Compare commits

...
303 Commits
Author SHA1 Message Date
Dave Horton 7dc3bbdb01 0.2.8 2025-05-08 09:31:40 -04:00
Dave Horton f8f9de2645 Merge pull request #110 from jambonz/feat/rimlabs_arcana
support rimelabs arcana
2025-05-06 09:22:35 -04:00
Quan HL 467d7ede26 support rimelabs arcana 2025-05-06 16:16:18 +07:00
Dave Horton fc211ab2e7 0.2.7 2025-04-28 19:31:59 -04:00
Dave Horton 536f8aab31 Merge pull request #109 from jambonz/feat/riva_tts
support riva tts stream
2025-04-28 19:31:30 -04:00
Hoan Luu Huu 69b3fdffbe Merge branch 'main' into feat/riva_tts 2025-04-28 08:47:44 +07:00
Dave Horton 53fe72d89e 0.2.6 2025-04-23 07:12:54 -04:00
Dave Horton e79c15c5da update version 2025-04-23 07:12:25 -04:00
Hoan Luu Huu a4a427e174 Merge branch 'main' into feat/riva_tts 2025-04-23 18:11:19 +07:00
Dave Horton b697bc5268 Merge pull request #108 from jambonz/feat/ell_tts_new_params
elevenlabs tts speed and pronunciation_dictionary_locators
2025-04-23 07:08:49 -04:00
Quan HL d35d7f0aec support riva tts stream 2025-04-23 17:54:21 +07:00
Quan HL ed1c564fa2 wip 2025-04-04 16:15:45 +07:00
Quan HL 7189d471c1 elevenlabs tts speed and pronunciation_dictionary_locators 2025-04-04 15:44:29 +07:00
Dave Horton 04080cc5ec 0.2.4 2025-03-19 21:48:31 -04:00
Dave Horton 3e5ab4af27 Merge pull request #107 from jambonz/update-deps
update undici
2025-03-19 21:48:02 -04:00
Dave Horton f06dddd2f7 update undici 2025-03-19 21:46:21 -04:00
Dave Horton 7b4a71f55d 0.2.3 2025-02-07 07:20:12 -05:00
Dave Horton d552b65618 Merge pull request #106 from jambonz/feat/rimelabs_voices
rimelabs support multiple model and languages
2025-02-07 07:19:47 -05:00
Quan HL f701b50244 rimelabs support multiple model and languages 2025-02-07 14:20:52 +07:00
Dave Horton 199e502fbe 0.2.2 2025-02-03 08:14:15 -05:00
Dave Horton 6769779189 Merge pull request #105 from jambonz/fix/gh_1059
tts key should include model
2025-02-03 08:13:54 -05:00
Quan HL 4b43c3986c wip 2025-02-02 19:03:09 +07:00
Quan HL e1292772e6 tts key should include model 2025-02-02 18:54:16 +07:00
Dave Horton 37fb045431 0.2.1 2024-12-18 22:16:43 -05:00
Dave Horton c328df67a2 major semver bump 2024-12-18 22:15:28 -05:00
Dave Horton 877cba7065 Merge pull request #103 from jambonz/feat/refactor_synth
remove audio extension from audio key
2024-12-18 22:13:52 -05:00
Quan HL 35a178b468 remove audio extension from audio key 2024-12-18 16:58:54 +07:00
Quan HL 7327190471 remove audio extension from audio key 2024-12-18 16:46:24 +07:00
Dave Horton e5b5e3d0c6 0.1.24 2024-12-16 07:27:18 -05:00
Dave Horton 3760be088b update deps 2024-12-16 07:26:49 -05:00
Dave Horton 5cb52eb8ec Merge pull request #101 from jambonz/feat/tts_cartesia
support cartesia tts
2024-12-16 07:25:29 -05:00
Quan HL 8a390a8edf support cartesia tts 2024-12-16 15:58:18 +07:00
Dave Horton d96ab5cdf3 Merge pull request #99 from jambonz/feat/support_aws_instance_profile
support aws instance profile to get key
2024-11-29 21:58:22 -05:00
Quan HL 3bf74671c6 support aws instance profile to get key 2024-11-30 08:40:26 +07:00
Dave Horton a47ef6d7c4 0.1.22 2024-11-04 07:38:23 -05:00
Dave Horton 84089fa528 Merge pull request #98 from jambonz/fix/freshdesk_411
Fix custom tts vendor cached file can not be played
2024-11-04 07:37:49 -05:00
Quan HL 72be44eea2 adding testcase 2024-11-04 15:53:11 +07:00
Quan HL 05d6c4b32d fixed custom vendor cache audio stores file extension 2024-11-04 15:43:44 +07:00
Dave Horton 0c7e15d0a2 0.1.21 2024-10-31 09:48:18 -04:00
Dave Horton 63efecf9d9 Merge pull request #97 from jambonz/feat/google_voice_cloning
support google voice cloning
2024-10-31 09:47:12 -04:00
Quan HL 153ac3f1a4 fix review comment 2024-10-31 20:30:35 +07:00
Quan HL 115faa9f89 support google voice cloning 2024-10-31 20:23:11 +07:00
Dave Horton f183852961 0.1.20 2024-10-18 12:23:26 -04:00
Dave Horton 34c3e01729 Merge pull request #95 from jambonz/fix/rimelabs
fix rimelabs typo issue on getFileExtension function
2024-10-18 12:22:52 -04:00
Quan HL 9b2b16199e fix rimelabs typo issue on getFileExtension function 2024-10-18 22:44:17 +07:00
Dave Horton 9112c5f0ea 0.1.19 2024-10-16 07:23:40 -04:00
Dave Horton 50783dfd0a Merge pull request #94 from jambonz/fix/playht30_lang
add language to playht3.0
2024-10-16 07:23:04 -04:00
Quan HL ca0ef76fe1 add language to playht3.0 2024-10-16 08:14:38 +07:00
Dave Horton 7c91c537e4 0.1.18 2024-10-11 07:33:37 -04:00
Dave Horton 9747526664 Merge pull request #93 from jambonz/fix/playht_3.0
fixed playht3.0 cannot be played if credential is cached
2024-10-11 07:32:57 -04:00
Quan HL 31a0c7b02c fixed playht3.0 cannot be played if credential is cached 2024-10-11 12:05:38 +07:00
Dave Horton c18fbacd1b update playht3 2024-10-09 13:29:01 -04:00
Dave Horton b0fee6bbf1 Merge pull request #92 from jambonz/feat/playht30
support playht3.0
2024-10-09 13:26:53 -04:00
Quan HL f6cead6e92 add top_p and repetition_penalty to playht3.0 2024-10-03 19:24:23 +07:00
Quan HL 05fc96edc0 wip 2024-09-27 18:24:03 +07:00
Quan HL 6794a0b3be support playht3.0 2024-09-27 12:25:47 +07:00
Quan HL 1a04fd736c support playht3.0 2024-09-27 12:08:41 +07:00
Dave Horton 1846203807 0.1.16 2024-09-16 15:53:14 -04:00
Dave Horton 75be8658c1 Merge pull request #91 from jambonz/fix/diff_playht_voice_quality
fix playht has stream and cached audio differrent quality
2024-09-16 15:52:42 -04:00
Quan HL 91a5eebbaf fixed review comment 2024-09-16 18:46:10 +07:00
Quan HL c96f1e86ee fix review comment 2024-09-16 18:15:45 +07:00
Quan HL 8016c0886a fix playht has stream and cached audio differrent quality 2024-09-16 09:01:45 +07:00
Dave Horton 8f216e64d8 0.1.15 2024-08-12 09:30:09 -04:00
Dave Horton e1f4486e01 bump version 2024-08-12 09:27:12 -04:00
Dave Horton b0d6272974 Merge pull request #84 from jambonz/feat/precache_audio_with_tts_stream
support precache audio with tts stream enabled
2024-08-12 09:26:00 -04:00
Quan HL ef23b0807a add comment 2024-08-12 20:16:24 +07:00
Quan HL ab7e25243d improve on check precache 2024-08-12 20:10:43 +07:00
Quan HL bf0ea14423 install docker 2024-08-12 18:40:47 +07:00
Quan HL 305dabd84b wip 2024-08-12 18:35:48 +07:00
Quan HL b6a3fa5081 support precache audio with tts stream enabled 2024-08-12 18:29:01 +07:00
Dave Horton 73feadc4c4 0.1.13 2024-08-06 11:01:09 -04:00
Dave Horton aad0f4d62c Merge pull request #82 from jambonz/feat/deepgram_tts_endpoint
deepgram tts support endpoint for on-premise
2024-08-06 11:00:38 -04:00
Hoan Luu Huu 602b0cc60e Merge branch 'main' into feat/deepgram_tts_endpoint 2024-07-31 14:03:41 +07:00
Dave Horton 8511e762c8 version update 2024-07-30 07:29:25 -04:00
Dave Horton b75d3068c9 Merge pull request #81 from jambonz/feat/gh_fs_832
allow configure STS session expiry
2024-07-30 07:14:06 -04:00
Quan HL 461178e726 wip 2024-07-29 20:56:55 +07:00
Quan HL e0e4d47340 wip 2024-07-29 20:53:55 +07:00
Quan HL a595faa378 deepgram tts support endpoint for on-premise 2024-07-29 19:45:13 +07:00
Quan HL 7fd1e1a3c3 allow configure STS session expiry 2024-07-29 18:18:37 +07:00
Dave Horton 7f6a3d349c 0.1.11 2024-06-14 07:37:19 -04:00
Dave Horton 50429ff535 bump version 2024-06-14 07:36:53 -04:00
Dave Horton 3bf0ef8ea3 Merge pull request #80 from jambonz/fix/aws_arnrole
fix aws arnrole
2024-06-14 07:34:22 -04:00
Quan HL e9a5e83e36 wip 2024-06-14 15:04:19 +07:00
Quan HL 86a64ac091 wip 2024-06-14 15:00:56 +07:00
Quan HL 97e06b3ab3 wip 2024-06-14 10:23:22 +07:00
Quan HL 09e833d910 wip 2024-06-14 10:19:55 +07:00
Quan HL 8c4e12e54f wip 2024-06-14 10:18:41 +07:00
Quan HL 2642bd71a4 wip 2024-06-14 10:16:57 +07:00
Quan HL c4feac916f fix aws arnrole 2024-06-14 10:15:23 +07:00
Dave Horton 2ec56f564e 0.1.9 2024-06-06 12:31:13 -04:00
Dave Horton 9399ddcb58 Merge pull request #78 from jambonz/env/disable-ms-streaming
Env/disable ms streaming
2024-06-06 12:30:48 -04:00
Dave Horton aebf4eda30 lint 2024-06-06 12:25:53 -04:00
Dave Horton 6b0bdfdf2f add env JAMBONES_DISABLE_AZURE_TTS_STREAMING to disable Microsoft TTS streaming 2024-06-06 12:25:08 -04:00
Dave Horton d214c3184f 0.1.8 2024-06-05 06:48:09 -04:00
Dave Horton c335a508a3 bump version 2024-06-05 06:47:01 -04:00
Dave Horton d7797d5691 Merge pull request #77 from jambonz/feat/improve_elevenlabs
support elevenlabs previous_text, next_text
2024-06-05 06:43:48 -04:00
Quan HL b81f3313cb support elevenlabs previous_text, next_text 2024-06-05 15:53:26 +07:00
Dave Horton 49fe64744c 0.1.6 2024-05-30 07:13:00 -04:00
Dave Horton 106238cca5 bump version 2024-05-30 07:12:37 -04:00
Dave Horton 01735ccf2f Merge pull request #76 from jambonz/fix/verbio_cache
fixed verbio tts extension
2024-05-30 07:10:50 -04:00
Quan HL ce81cb8d24 fixed verbio tts extension 2024-05-30 16:13:05 +07:00
Dave Horton c9d7a9046f 0.1.4 2024-05-29 07:24:07 -04:00
Dave Horton a9ba383667 Merge pull request #75 from Catharsis68/feat/pre-commit-hook
Update eslint, add pre commit hook
2024-05-29 07:23:41 -04:00
Markus Frindt 06b97bcb0f Update eslint, add pre commit hook 2024-05-29 10:22:10 +02:00
Dave Horton 90152b36ef 0.1.3 2024-05-28 13:02:15 -04:00
Dave Horton 92484b7441 Merge pull request #74 from jambonz/fix/lint
lint
2024-05-28 13:01:35 -04:00
Dave Horton 398904785b lint 2024-05-28 12:58:37 -04:00
Dave Horton 531fa21f88 0.1.2 2024-05-28 12:55:00 -04:00
Dave Horton 904495d819 Merge pull request #73 from Catharsis68/feat/tts-cache-improvement
Improve handling of TTS cache by adding the file extension to the cac…
2024-05-28 12:54:31 -04:00
Markus Frindt f13fc84853 merge latest main into feature branch 2024-05-28 18:44:41 +02:00
Dave Horton e099bbb58f 0.1.1 2024-05-28 09:43:24 -04:00
Dave Horton e60a2d2ba3 Merge pull request #72 from jambonz/feat/verbio_speech
add verbio tts/stt
2024-05-28 09:42:28 -04:00
Markus Frindt 39d54050cc simplify return for streaming responses 2024-05-28 15:23:53 +02:00
Markus Frindt 7618d334db add namespace for custom provider 2024-05-27 11:04:35 +02:00
Markus Frindt 71f20178d3 add test case 2024-05-24 14:09:07 +02:00
Markus Frindt cb6ab2479f Improve handling of TTS cache by adding the file extension to the cache key 2024-05-24 14:03:31 +02:00
Quan HL 2212be341b add synthesize verbio 2024-05-20 18:11:01 +07:00
Quan HL 5d2d921f31 add verbio tts/stt 2024-05-20 17:24:06 +07:00
Dave Horton acb2d0c7ce Merge pull request #71 from jambonz/feat/azure_private_endpoint
support tts stream private endpoint
2024-05-14 06:56:51 -04:00
Quan HL 90d6048f52 fix private azure link with credential 2024-05-14 14:01:25 +07:00
Quan HL e5985620c0 support tts stream private endpoint 2024-05-05 14:28:11 +07:00
Dave Horton eb57f4d290 bump version 2024-05-02 07:46:47 -04:00
Dave Horton f0a1ab139c Merge pull request #69 from jambonz/feat/aws_polly_rolearn
support AWS Polly RoleArn credential
2024-05-02 07:44:38 -04:00
Quan HL 79289a7249 wip 2024-05-02 15:51:45 +07:00
Quan HL 5998eebdca wip 2024-05-02 15:48:20 +07:00
Quan HL e6a7017b55 wip 2024-05-02 14:20:24 +07:00
Quan HL c8571af129 wip 2024-04-30 15:47:14 +07:00
Quan HL 6144a9c164 wip 2024-04-30 15:45:26 +07:00
Quan HL 68a7f2b0d4 wip 2024-04-30 15:45:10 +07:00
Quan HL 0d1cd37097 wip 2024-04-30 11:20:21 +07:00
Quan HL 3de8e5ff57 accept aws polly without credential 2024-04-22 20:02:59 +07:00
Quan HL b4aad7991b update get aws voices 2024-04-22 16:19:04 +07:00
Quan HL 8a5c5c1966 support mod_google_tts 2024-04-19 16:06:53 +07:00
Quan HL 08a56d1a40 support AWS Polly RoleArn credential 2024-04-19 15:30:22 +07:00
Dave Horton ba61f20334 0.0.51 2024-04-12 07:19:56 -04:00
Dave Horton 10316d786e Merge pull request #67 from jambonz/feat/mod_rimelabs_tts
support mod_rimelabs_tts
2024-04-12 07:10:32 -04:00
Quan HL 38cdc106cc wip 2024-04-12 17:55:55 +07:00
Quan HL 410b99ef24 support mod_rimelabs_tts 2024-04-12 15:57:02 +07:00
Dave Horton 51db63f992 Merge pull request #66 from jambonz/gh-actions
add PlayHT to CI test
2024-04-08 09:49:48 -04:00
Dave Horton c86dceadde add PlayHT to CI test 2024-04-08 09:47:04 -04:00
Dave Horton f56f98f40f 0.0.50 2024-04-08 09:44:17 -04:00
Dave Horton 12a36593aa Merge pull request #65 from jambonz/feat/mod_playht_tts
support mod_playht_tts
2024-04-08 09:43:00 -04:00
Quan HL 8382491477 wip 2024-04-08 20:31:56 +07:00
Quan HL 545d559e27 wip 2024-04-08 19:14:58 +07:00
Quan HL cc8963802f wip 2024-04-08 17:33:21 +07:00
Quan HL 282d87f922 wip 2024-04-08 17:24:15 +07:00
Quan HL 6a288c1db0 support mod_playht_tts 2024-04-08 17:20:32 +07:00
Dave Horton 8650328e64 0.0.49 2024-04-07 12:15:02 -04:00
Dave Horton 85fa6da5b5 update to azure speech sdk 1.36.0 2024-04-07 12:14:55 -04:00
Dave Horton e54e913fdd 0.0.48 2024-04-04 15:52:40 -04:00
Dave Horton b088c0d7d9 Merge pull request #63 from jambonz/feat/mod_deepgram_tts
Feat/mod deepgram tts
2024-04-04 15:52:10 -04:00
Hoan Luu Huu f154a40692 Merge branch 'main' into feat/mod_deepgram_tts 2024-04-04 18:58:38 +07:00
Quan HL 0471b94ebe wip 2024-04-04 10:12:24 +07:00
Dave Horton 8279891dff 0.0.47 2024-04-03 13:33:24 -04:00
Dave Horton f546ca998d cache files for azure tts streaming are r8 2024-04-03 13:32:32 -04:00
Dave Horton bf229d0ab0 0.0.46 2024-04-03 13:22:20 -04:00
Dave Horton f08fedb8ca enable caching from azure tts streaming 2024-04-03 13:17:36 -04:00
Quan HL f3cc38089c mod_deepgra_tts 2024-04-03 20:46:52 +07:00
Dave Horton fbed59e5de 0.0.45 2024-04-02 15:10:54 -04:00
Dave Horton 4f1685a365 Merge pull request #59 from jambonz/feat/azure_tts
support azure streaming
2024-03-30 09:21:07 -04:00
Quan HL 2701af102a wip 2024-03-30 17:49:14 +07:00
Quan HL 7f939b96d2 wip 2024-03-30 17:38:00 +07:00
Quan HL 4d58ca6daf wip 2024-03-30 17:34:49 +07:00
Hoan Luu Huu 16dd7a2805 Merge branch 'main' into feat/azure_tts 2024-03-30 17:04:01 +07:00
Dave Horton 8f3e930004 0.0.44 2024-03-20 19:43:26 -04:00
Dave Horton 3f4c444d82 add azure SSML tests 2024-03-20 19:43:18 -04:00
Hoan Luu Huu fd7d8b8bcd Merge pull request #62 from jambonz/feat/mod_dub
say command for freeswitch module to include vendor and voice
2024-03-20 13:40:51 +07:00
Hoan Luu Huu 46f833c7fa Merge branch 'main' into feat/mod_dub 2024-03-12 18:10:21 +07:00
Dave Horton 4eabfbe4b7 0.0.43 2024-03-11 09:25:14 -04:00
Quan HL f3ab2baa6a wip 2024-03-10 07:34:55 +07:00
Hoan Luu Huu fb412e2ddf Merge branch 'main' into feat/mod_dub 2024-03-10 06:43:09 +07:00
Quan HL f06f96a6f0 wip 2024-03-10 06:41:46 +07:00
Hoan Luu Huu 2988e800b1 Merge branch 'main' into feat/azure_tts 2024-03-10 06:39:00 +07:00
Dave Horton dbfabeaddf Merge pull request #61 from jambonz/fix/duplicate-calls
remove seemingly redundant code, reintroduce param to force bypass of…
2024-03-09 18:25:15 -05:00
Quan HL c3188e40bb support mod_dub 2024-03-09 16:59:00 +07:00
Dave Horton d0dfd07204 remove seemingly redundant code, reintroduce param to force bypass of tts streaming 2024-03-07 13:44:40 -05:00
Dave Horton 04a2466f54 Merge pull request #60 from jambonz/fix/deepgram_tts
update deepgram tts endpoint
2024-03-05 09:12:58 -05:00
Quan HL 0f9a9edc4d update deepgram tts endpoint 2024-03-05 20:55:19 +07:00
Quan HL 31a54f595b wip 2024-02-26 15:42:09 +07:00
Quan HL 3560a6d4d9 wip 2024-02-26 14:01:53 +07:00
Quan HL be8053db4f wip 2024-02-26 13:54:34 +07:00
Quan HL 4ffae38a3f wip 2024-02-26 13:49:37 +07:00
Quan HL 9e74760c39 support azure streaming 2024-02-26 13:33:22 +07:00
Dave Horton ced1a0ef0d 0.0.42 2024-02-20 20:34:51 -05:00
Dave Horton 1609d0b205 Merge pull request #57 from jambonz/feat/whisper_tts_stream
support whisper streaming
2024-02-20 20:33:21 -05:00
Quan HL ef8ada2793 wip 2024-02-20 20:52:14 +07:00
Quan HL 444ad2522f rebase 2024-02-19 15:32:50 +07:00
Dave Horton 1caea60803 0.0.41 2024-02-12 21:06:48 -05:00
Dave Horton 97c3588cfd bug: JAMBONES_DISABLE_TTS_STREAMING is now the env 2024-02-12 21:06:38 -05:00
Dave Horton da3aa5aadb 0.0.40 2024-02-12 12:43:11 -05:00
Dave Horton 2fe89f132c change elevenlabs default to streaming, can be disabled by env 2024-02-12 12:41:21 -05:00
Dave Horton 4bca840ba2 0.0.39 2024-02-08 14:55:50 -05:00
Dave Horton f858ccb781 for tts streaming we need to replace CR and LF with spaces, as we can not send text with those characters to freeswitch currently 2024-02-08 14:55:39 -05:00
Quan HL 3cf9894b44 support whisper streaming 2024-02-05 11:49:38 +07:00
Dave Horton 436b15d648 0.0.38 2024-01-26 11:09:24 -05:00
Dave Horton c3b7ea4cd1 fix prev commit 2024-01-26 11:08:06 -05:00
Dave Horton 4b5430d61d 0.0.37 2024-01-26 09:54:51 -05:00
Dave Horton 9fc8fe8341 Merge pull request #56 from jambonz/feat/cache-streaming
add function to add an audio file generated externally to cache
2024-01-26 09:54:24 -05:00
Dave Horton b31e40b8a5 add function to add an audio file generated externally to cache 2024-01-26 09:52:32 -05:00
Dave Horton 62e1c69f69 0.0.36 2024-01-25 13:14:31 -05:00
Dave Horton bc68b672ac Merge pull request #55 from jambonz/tts-streaming-cache-attribute
add tts param to indicate caching
2024-01-25 13:14:00 -05:00
Dave Horton da1e279128 add tts param to indicate caching 2024-01-25 13:07:49 -05:00
Dave Horton 60bcfe07d7 0.0.35 2024-01-25 09:40:14 -05:00
Dave Horton d343c81088 Merge pull request #54 from jambonz/feat/fix_getVoice_aws
fix get aws voice should not be limit in en-US
2024-01-25 09:39:36 -05:00
Quan HL 706f6d5808 fix get aws voice should not be limit in en-US 2024-01-25 21:37:38 +07:00
Dave Horton 1b1a0f19d0 0.0.34 2024-01-22 15:18:21 -05:00
Dave Horton 119ac50f7f Merge pull request #53 from jambonz/elevenlabs-streaming
Elevenlabs streaming
2024-01-22 15:17:33 -05:00
Dave Horton cb479f04d5 add param to synthAuydio to indicate whether audio is being generated specifically for caching purposes 2024-01-22 08:10:00 -05:00
Dave Horton 7e21e0b666 changes to support elevenlabs tts streaming 2024-01-21 21:36:53 -05:00
Dave Horton dabdb5b584 if streaming env is set prepare to use streaming tts 2024-01-20 14:15:13 -05:00
Dave Horton f36ba027d0 0.0.33 2023-12-25 22:13:29 -05:00
Dave Horton 08aae32975 Merge pull request #51 from jambonz/feat/deepgram
support deepgram
2023-12-25 22:10:50 -05:00
Quan HL 4cfc730d92 support deepgram 2023-12-26 09:26:31 +07:00
Dave Horton 4ef8538bcd 0.0.32 2023-12-18 10:21:12 -05:00
Dave Horton 16a746398f add CI badge to README 2023-12-06 10:06:43 -05:00
Dave Horton 4a75f353ee Merge pull request #35 from jambonz/feature/azure-proxy-support
add support for SetProxy when using azure tts
2023-12-06 09:57:11 -05:00
Dave Horton bbff7963fd make test explicit 2023-12-06 09:54:19 -05:00
Dave Horton 7b1d226403 test proxy using azure 2023-12-06 09:54:16 -05:00
Dave Horton 95c29ce105 squid config file so we can test azure proxy setting 2023-12-06 09:53:35 -05:00
Dave Horton a46ae01d9c add support for JAMBONES_HTTP_PROXY_IP and JAMBONES_HTTP_PROXY_PORT for azure tts 2023-12-06 09:53:35 -05:00
Dave Horton 562dd0ac79 0.0.31 2023-12-05 20:36:43 -05:00
Dave Horton a0612bd1f9 Merge pull request #50 from jambonz/fix/reuse_redis
cannot assign redis-client as createHash and retrieveHash
2023-12-03 19:58:58 -05:00
Quan HL 2dcbf2b0f1 cannot assign redis-client as createHash and retrieveHash 2023-12-04 06:17:02 +07:00
Dave Horton 048b7e871e 0.0.30 2023-11-30 16:11:34 -05:00
Dave Horton 4cae96eacb rename aws token from sessionToken to securityToken for consistency with AWS docs 2023-11-30 16:11:23 -05:00
Dave Horton 1e57d00b55 0.0.29 2023-11-30 08:56:56 -05:00
Dave Horton 4ead5ee417 Merge pull request #47 from jambonz/feat/update_elevenlabs
support elevenlabs options
2023-11-30 08:53:19 -05:00
Quan HL a517f37473 wip 2023-11-30 16:37:44 +07:00
Quan HL 3ac5a98e3a get elevenlabs options from syntheizier.options 2023-11-30 15:56:22 +07:00
Quan HL 689fab6857 get elevenlabs options from syntheizier.options 2023-11-30 15:48:26 +07:00
Quan HL be3c484527 support elevenlabs options 2023-11-30 13:29:51 +07:00
Dave Horton 9827f7405d 0.0.28 2023-11-29 14:17:58 -05:00
Dave Horton 906a6b52b8 fix issue with conflicting EC2 permissions calling AWS STS 2023-11-29 14:17:46 -05:00
Dave Horton 1f0b9ff539 0.0.27 2023-11-27 09:45:39 -05:00
Dave Horton b6f8368357 Merge pull request #46 from jambonz/feat/aws-sts-auth-token
Feat/aws sts auth token
2023-11-27 09:44:38 -05:00
Dave Horton 6bc487b3d1 logging 2023-11-27 09:37:49 -05:00
Dave Horton 9699abe0a3 dowgrade azure to 1.32.0 per: https://github.com/microsoft/cognitive-services-speech-sdk-js/issues/752 2023-11-27 09:32:03 -05:00
Dave Horton 5e1e7b17c6 remove console logging in tests 2023-11-27 09:27:18 -05:00
Dave Horton 1f52cd4f08 added function to get an AWS security token using STS 2023-11-27 09:26:41 -05:00
Dave Horton 7df4e2f4c7 0.0.26 2023-11-14 08:48:14 -05:00
Dave Horton e99f7c5087 Merge pull request #43 from jambonz/feat/realtimedb
use realtimedb-helper for initiate redis connection
2023-11-10 07:49:28 -05:00
Quan HL c7d981c23a wip 2023-11-10 10:37:22 +07:00
Quan HL 95c54b9b12 use realtimedb-helper for initiate redis connection 2023-11-10 10:34:50 +07:00
Dave Horton 48192aeba1 Merge pull request #42 from jambonz/gh-actions
update gihub actions to test openai and elevenlabs
2023-11-09 08:44:14 -05:00
Dave Horton 8f931cd8a5 update gihub actions to test openai and elevenlabs 2023-11-09 08:42:32 -05:00
Dave Horton 144baafe94 0.0.25 2023-11-09 08:32:07 -05:00
Dave Horton ed3e513419 fix google speech test 2023-11-09 08:31:59 -05:00
Dave Horton 8d93fdc42a Merge pull request #41 from jambonz/feat/openai
support whisper tts
2023-11-09 08:30:24 -05:00
Quan HL ea523a7a1d wip 2023-11-09 12:59:20 +07:00
Quan HL 750ed97312 update review 2023-11-09 09:19:47 +07:00
Quan HL 73baa81177 update review 2023-11-09 09:15:54 +07:00
Quan HL f86234a769 support openai 2023-11-09 07:10:07 +07:00
Dave Horton d564f24e6c 0.0.24 2023-10-30 19:54:56 -04:00
Dave Horton 464d8462d9 Merge pull request #39 from jambonz/feat/google_custom_voice_01
fix google custom voice
2023-10-30 19:54:44 -04:00
Quan HL 6853f0e342 fix google custom voice 2023-10-31 06:24:52 +07:00
Dave Horton 507045dcba 0.0.23 2023-10-29 22:07:02 -04:00
Dave Horton 08758bbbff Merge pull request #38 from jambonz/feat/google_custom_voice
feat support google custom voice
2023-10-29 22:06:41 -04:00
Hoan Luu Huu a3aa1169b8 feat support google custom voice 2023-10-30 01:55:50 +00:00
Hoan Luu Huu 7cae19a4e5 feat support google custom voice 2023-10-30 01:54:02 +00:00
Hoan Luu Huu 8c4d5a7cee feat support google custom voice 2023-10-30 01:52:48 +00:00
Dave Horton eb2c39072b 0.0.22 2023-10-14 13:18:08 +02:00
Dave Horton e5932ffc18 Merge pull request #34 from jambonz/feat/elevenlabs
add elevenlabs
2023-10-14 07:17:14 -04:00
Quan HL 0a98c6a376 fix review comment 2023-10-14 18:13:04 +07:00
Quan HL ea153e9833 add elevenlabs 2023-10-12 14:22:15 +07:00
Dave Horton b5daeff047 0.0.21 2023-09-08 07:58:11 -04:00
Dave Horton da02926c9a Merge pull request #31 from jambonz/fix/onprem-azure
fix raw audio downloaded from onprem azure
2023-09-08 07:57:36 -04:00
Quan HL da3cdbb7aa fix raw audio downloaded from onprem azure 2023-09-08 15:42:57 +07:00
Dave Horton 625f147137 0.0.20 2023-08-30 21:08:52 -04:00
Dave Horton 2e5687978e 0.0.19 2023-08-30 21:08:41 -04:00
Dave Horton 897481d34c Merge pull request #29 from jambonz/feat/azure_fromhost
support self hosted microsoft
2023-08-30 21:07:44 -04:00
Quan HL bd5282e681 fix 2023-08-28 20:05:55 +07:00
Quan HL 95a1384f02 wip 2023-08-25 15:57:43 +07:00
Quan HL 35deeecf70 wip 2023-08-25 15:57:23 +07:00
Quan HL 9d2ac3273f wip 2023-08-25 13:53:09 +07:00
Quan HL b1049aad7f wip 2023-08-25 13:49:04 +07:00
Quan HL 40f51e7509 wip 2023-08-11 18:25:57 +07:00
Quan HL a0e2fe167c wip 2023-08-11 16:04:11 +07:00
Quan HL 1fa853faa3 wip 2023-08-11 13:30:11 +07:00
Quan HL 95e8d942b8 fix jslint 2023-08-09 18:00:17 +07:00
Quan HL 7a91876cd7 support self hosted microsoft 2023-08-09 17:56:38 +07:00
Dave Horton d07344ba3b Merge pull request #28 from jambonz/revert/ssml-silence-trim
revert change to _not_ trim silence when azure ssml is used
2023-07-25 12:34:22 -04:00
Dave Horton 44d8af2a96 revert change to _not_ trim silence when azure ssml is used 2023-07-25 11:08:06 -04:00
Dave Horton b530db9a62 0.0.18 2023-07-25 07:40:33 -04:00
Dave Horton 4c166c8eb4 synth_audio: dont trim silence for Azure when using SSML 2023-07-25 07:40:28 -04:00
Dave Horton 8246dbea21 0.0.17 2023-07-19 10:10:39 -04:00
Dave Horton 0084f6a468 update deps 2023-07-19 10:09:31 -04:00
Dave Horton 98f679f43a 0.0.16 2023-07-19 10:04:17 -04:00
Dave Horton 7e7841b5ff Merge pull request #23 from jambonz/feature/trim-silence
trim trailing silence from azure tts when JAMBONES_TTS_TRIM_SILENCE i…
2023-07-19 10:03:42 -04:00
Dave Horton 75ce537db1 linting 2023-07-19 10:02:10 -04:00
Dave Horton 830be783b8 trim trailing silence from azure tts when JAMBONES_TTS_TRIM_SILENCE is set 2023-07-19 10:00:31 -04:00
Dave Horton 38c3219425 Merge pull request #21 from jambonz/snyk-fix-255777535fcb48b70c964213f7dd9fe8
[Snyk] Security upgrade @aws-sdk/client-polly from 3.303.0 to 3.347.1
2023-06-07 13:09:27 -04:00
snyk-bot e37b96a9c2 fix: package.json & package-lock.json to reduce vulnerabilities
The following vulnerabilities are fixed with an upgrade:
- https://snyk.io/vuln/SNYK-JS-FASTXMLPARSER-5668858
2023-06-07 15:35:04 +00:00
Dave Horton c184fbae26 0.0.15 2023-06-03 09:15:48 -04:00
Dave Horton 66d33ebd60 change default tts cache duration to 4 hours 2023-06-03 09:15:45 -04:00
Dave Horton 98e1bf62f9 0.0.14 2023-05-31 11:15:38 -04:00
Dave Horton 63edbc2883 Merge pull request #20 from jambonz/feat/clear_tts
feat: ioredis and getsize of tts cache
2023-05-31 11:13:48 -04:00
Quan HL fb75de6af5 feat: ioredis and getsize of tts cache 2023-05-31 21:56:50 +07:00
Quan HL 617f7af4af feat: ioredis and getsize of tts cache 2023-05-31 21:53:18 +07:00
Dave Horton 6c5c8e734f 0.0.13 2023-05-10 07:39:21 -04:00
Dave Horton 4349cd7e40 Merge pull request #19 from jambonz/fix/nvidia
fixes for riva tts
2023-05-10 07:38:58 -04:00
Dave Horton b6058ca242 fix nvidia test 2023-05-10 07:36:25 -04:00
Dave Horton 68cbd63bbd minor logging 2023-05-09 13:59:38 -04:00
Dave Horton 521560e276 fixes for riva tts 2023-05-09 13:57:41 -04:00
32 changed files with 7359 additions and 5156 deletions
-1
View File
@@ -1 +0,0 @@
test/*
-126
View File
@@ -1,126 +0,0 @@
{
"env": {
"node": true,
"es6": true
},
"parserOptions": {
"ecmaFeatures": {
"jsx": false,
"modules": false
},
"ecmaVersion": 2020
},
"plugins": ["promise"],
"rules": {
"promise/always-return": "error",
"promise/no-return-wrap": "error",
"promise/param-names": "error",
"promise/catch-or-return": "error",
"promise/no-native": "off",
"promise/no-nesting": "warn",
"promise/no-promise-in-callback": "warn",
"promise/no-callback-in-promise": "warn",
"promise/no-return-in-finally": "warn",
// Possible Errors
// http://eslint.org/docs/rules/#possible-errors
"comma-dangle": [2, "only-multiline"],
"no-control-regex": 2,
"no-debugger": 2,
"no-dupe-args": 2,
"no-dupe-keys": 2,
"no-duplicate-case": 2,
"no-empty-character-class": 2,
"no-ex-assign": 2,
"no-extra-boolean-cast" : 2,
"no-extra-parens": [2, "functions"],
"no-extra-semi": 2,
"no-func-assign": 2,
"no-invalid-regexp": 2,
"no-irregular-whitespace": 2,
"no-negated-in-lhs": 2,
"no-obj-calls": 2,
"no-proto": 2,
"no-unexpected-multiline": 2,
"no-unreachable": 2,
"use-isnan": 2,
"valid-typeof": 2,
// Best Practices
// http://eslint.org/docs/rules/#best-practices
"no-fallthrough": 2,
"no-octal": 2,
"no-redeclare": 2,
"no-self-assign": 2,
"no-unused-labels": 2,
// Strict Mode
// http://eslint.org/docs/rules/#strict-mode
"strict": [2, "never"],
// Variables
// http://eslint.org/docs/rules/#variables
"no-delete-var": 2,
"no-undef": 2,
"no-unused-vars": [2, {"args": "none"}],
// Node.js and CommonJS
// http://eslint.org/docs/rules/#nodejs-and-commonjs
"no-mixed-requires": 2,
"no-new-require": 2,
"no-path-concat": 2,
"no-restricted-modules": [2, "sys", "_linklist"],
// Stylistic Issues
// http://eslint.org/docs/rules/#stylistic-issues
"comma-spacing": 2,
"eol-last": 2,
"indent": [2, 2, {"SwitchCase": 1}],
"keyword-spacing": 2,
"max-len": [2, 120, 2],
"new-parens": 2,
"no-mixed-spaces-and-tabs": 2,
"no-multiple-empty-lines": [2, {"max": 2}],
"no-trailing-spaces": [2, {"skipBlankLines": false }],
"quotes": [2, "single", "avoid-escape"],
"semi": 2,
"space-before-blocks": [2, "always"],
"space-before-function-paren": [2, "never"],
"space-in-parens": [2, "never"],
"space-infix-ops": 2,
"space-unary-ops": 2,
// ECMAScript 6
// http://eslint.org/docs/rules/#ecmascript-6
"arrow-parens": [2, "always"],
"arrow-spacing": [2, {"before": true, "after": true}],
"constructor-super": 2,
"no-class-assign": 2,
"no-confusing-arrow": 2,
"no-const-assign": 2,
"no-dupe-class-members": 2,
"no-new-symbol": 2,
"no-this-before-super": 2,
"prefer-const": 2
},
"globals": {
"DTRACE_HTTP_CLIENT_REQUEST" : false,
"LTTNG_HTTP_CLIENT_REQUEST" : false,
"COUNTER_HTTP_CLIENT_REQUEST" : false,
"DTRACE_HTTP_CLIENT_RESPONSE" : false,
"LTTNG_HTTP_CLIENT_RESPONSE" : false,
"COUNTER_HTTP_CLIENT_RESPONSE" : false,
"DTRACE_HTTP_SERVER_REQUEST" : false,
"LTTNG_HTTP_SERVER_REQUEST" : false,
"COUNTER_HTTP_SERVER_REQUEST" : false,
"DTRACE_HTTP_SERVER_RESPONSE" : false,
"LTTNG_HTTP_SERVER_RESPONSE" : false,
"COUNTER_HTTP_SERVER_RESPONSE" : false,
"DTRACE_NET_STREAM_END" : false,
"LTTNG_NET_STREAM_END" : false,
"COUNTER_NET_SERVER_CONNECTION_CLOSE" : false,
"DTRACE_NET_SERVER_CONNECTION" : false,
"LTTNG_NET_SERVER_CONNECTION" : false,
"COUNTER_NET_SERVER_CONNECTION" : false
}
}
+19 -3
View File
@@ -8,12 +8,20 @@ jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/setup-node@v3
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: lts/*
- run: npm install
- name: Install Docker Compose
run: |
sudo curl -L "https://github.com/docker/compose/releases/download/1.29.2/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
sudo chmod +x /usr/local/bin/docker-compose
docker-compose --version
- run: npm run jslint
- run: sudo apt update && sudo apt install -y squid
- run: sudo cp test/squid.conf /etc/squid/squid.conf
- run: sudo systemctl start squid
- run: npm test
env:
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
@@ -24,4 +32,12 @@ jobs:
IBM_TTS_API_KEY: ${{ secrets.IBM_TTS_API_KEY }}
IBM_TTS_REGION: ${{ secrets.IBM_TTS_REGION }}
MICROSOFT_API_KEY: ${{ secrets.MICROSOFT_API_KEY }}
MICROSOFT_REGION: ${{ secrets.MICROSOFT_REGION }}
MICROSOFT_REGION: ${{ secrets.MICROSOFT_REGION }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY }}
ELEVENLABS_VOICE_ID: ${{ secrets.ELEVENLABS_VOICE_ID }}
ELEVENLABS_MODEL_ID: ${{ secrets.ELEVENLABS_MODEL_ID }}
PLAYHT_USER_ID: ${{ secrets.PLAYHT_USER_ID }}
PLAYHT_API_KEY: ${{ secrets.PLAYHT_API_KEY }}
JAMBONES_HTTP_PROXY_IP: 127.0.0.1
JAMBONES_HTTP_PROXY_PORT: 3128
+2
View File
@@ -39,3 +39,5 @@ node_modules
examples/*
.vscode
.env
+3
View File
@@ -0,0 +1,3 @@
#npm audit
npm run jslint:fix || true
npm test
+3 -2
View File
@@ -1,2 +1,3 @@
# speech-utils
TTS-related speech utilities for jambonz
# speech-utils ![CI](https://github.com/jambonz/speech-utils/workflows/CI/badge.svg)
TTS-related speech utilities for jambonz.
+3 -1
View File
@@ -8,6 +8,8 @@
},
"redis-auth": {
"host": "127.0.0.1",
"port": 3380
"port": 3380,
"username": "daveh",
"password": "foobarbazzle"
}
}
+140
View File
@@ -0,0 +1,140 @@
const promise = require('eslint-plugin-promise');
const globals = require('globals');
module.exports = [
{
files: ['**/*.js', '*.js'],
languageOptions: {
ecmaVersion: 2020,
parserOptions: {
'node': true,
'es6': true,
ecmaFeatures: {
jsx: false,
modules: false,
}
},
sourceType: 'module',
globals: {
...globals.node,
'DTRACE_HTTP_CLIENT_REQUEST': false,
'LTTNG_HTTP_CLIENT_REQUEST': false,
'COUNTER_HTTP_CLIENT_REQUEST': false,
'DTRACE_HTTP_CLIENT_RESPONSE': false,
'LTTNG_HTTP_CLIENT_RESPONSE': false,
'COUNTER_HTTP_CLIENT_RESPONSE': false,
'DTRACE_HTTP_SERVER_REQUEST': false,
'LTTNG_HTTP_SERVER_REQUEST': false,
'COUNTER_HTTP_SERVER_REQUEST': false,
'DTRACE_HTTP_SERVER_RESPONSE': false,
'LTTNG_HTTP_SERVER_RESPONSE': false,
'COUNTER_HTTP_SERVER_RESPONSE': false,
'DTRACE_NET_STREAM_END': false,
'LTTNG_NET_STREAM_END': false,
'COUNTER_NET_SERVER_CONNECTION_CLOSE': false,
'DTRACE_NET_SERVER_CONNECTION': false,
'LTTNG_NET_SERVER_CONNECTION': false,
'COUNTER_NET_SERVER_CONNECTION': false
},
},
'plugins': {
promise
},
'rules': {
'promise/always-return': 'error',
'promise/no-return-wrap': 'error',
'promise/param-names': 'error',
'promise/catch-or-return': 'error',
'promise/no-native': 'off',
'promise/no-nesting': 'warn',
'promise/no-promise-in-callback': 'warn',
'promise/no-callback-in-promise': 'warn',
'promise/no-return-in-finally': 'warn',
// Possible Errors
// http://eslint.org/docs/rules/#possible-errors
'comma-dangle': [2, 'only-multiline'],
'no-control-regex': 2,
'no-debugger': 2,
'no-dupe-args': 2,
'no-dupe-keys': 2,
'no-duplicate-case': 2,
'no-empty-character-class': 2,
'no-ex-assign': 2,
'no-extra-boolean-cast': 2,
'no-extra-parens': [2, 'functions'],
'no-extra-semi': 2,
'no-func-assign': 2,
'no-invalid-regexp': 2,
'no-irregular-whitespace': 2,
'no-negated-in-lhs': 2,
'no-obj-calls': 2,
'no-proto': 2,
'no-unexpected-multiline': 2,
'no-unreachable': 2,
'use-isnan': 2,
'valid-typeof': 2,
// Best Practices
// http://eslint.org/docs/rules/#best-practices
'no-fallthrough': 2,
'no-octal': 2,
'no-redeclare': 2,
'no-self-assign': 2,
'no-unused-labels': 2,
// Strict Mode
// http://eslint.org/docs/rules/#strict-mode
'strict': [2, 'never'],
// Variables
// http://eslint.org/docs/rules/#variables
'no-delete-var': 2,
'no-undef': 2,
'no-unused-vars': [2, { 'args': 'none' }],
// Node.js and CommonJS
// http://eslint.org/docs/rules/#nodejs-and-commonjs
'no-mixed-requires': 2,
'no-new-require': 2,
'no-path-concat': 2,
'no-restricted-modules': [2, 'sys', '_linklist'],
// Stylistic Issues
// http://eslint.org/docs/rules/#stylistic-issues
'comma-spacing': 2,
'eol-last': 2,
'indent': [2, 2, { 'SwitchCase': 1 }],
'keyword-spacing': 2,
'max-len': [2, 120, 2],
'new-parens': 2,
'no-mixed-spaces-and-tabs': 2,
'no-multiple-empty-lines': [2, { 'max': 2 }],
'no-trailing-spaces': [2, { 'skipBlankLines': false }],
'quotes': [2, 'single', 'avoid-escape'],
'semi': 2,
'space-before-blocks': [2, 'always'],
'space-before-function-paren': [2, 'never'],
'space-in-parens': [2, 'never'],
'space-infix-ops': 2,
'space-unary-ops': 2,
// ECMAScript 6
// http://eslint.org/docs/rules/#ecmascript-6
'arrow-parens': [2, 'always'],
'arrow-spacing': [2, { 'before': true, 'after': true }],
'constructor-super': 2,
'no-class-assign': 2,
'no-confusing-arrow': 2,
'no-const-assign': 2,
'no-dupe-class-members': 2,
'no-new-symbol': 2,
'no-this-before-super': 2,
'prefer-const': 2
},
'ignores': []
}
];
+11 -20
View File
@@ -1,32 +1,23 @@
const {noopLogger} = require('./lib/utils');
const promisify = require('@jambonz/promisify-redis');
const redis = promisify(require('redis'));
module.exports = (opts, logger) => {
const {host = '127.0.0.1', port = 6379, tls = false} = opts;
logger = logger || noopLogger;
const url = process.env.JAMBONES_REDIS_USERNAME && process.env.JAMBONES_REDIS_PASSWORD ?
`${process.env.JAMBONES_REDIS_USERNAME}:${process.env.JAMBONES_REDIS_PASSWORD}@${host}:${port}` :
`${host}:${port}`;
const client = redis.createClient(tls ? `rediss://${url}` : `redis://${url}`);
['ready', 'connect', 'reconnecting', 'error', 'end', 'warning']
.forEach((event) => {
client.on(event, (...args) => {
if ('error' === event) {
if (process.env.NODE_ENV === 'test' && args[0]?.code === 'ECONNREFUSED') return;
logger.error({...args}, '@jambonz/realtimedb-helpers - redis error');
}
else logger.debug({args}, `redis event ${event}`);
});
});
const {
client,
createHash,
retrieveHash
} = require('@jambonz/realtimedb-helpers')(opts, logger);
return {
client,
getTtsSize: require('./lib/get-tts-size').bind(null, client, logger),
purgeTtsCache: require('./lib/purge-tts-cache').bind(null, client, logger),
synthAudio: require('./lib/synth-audio').bind(null, client, logger),
addFileToCache: require('./lib/add-file-to-cache').bind(null, client, logger),
synthAudio: require('./lib/synth-audio').bind(null, client, createHash, retrieveHash, logger),
getVerbioAccessToken: require('./lib/get-verbio-token').bind(null, client, logger),
getNuanceAccessToken: require('./lib/get-nuance-access-token').bind(null, client, logger),
getIbmAccessToken: require('./lib/get-ibm-access-token').bind(null, client, logger),
getTtsVoices: require('./lib/get-tts-voices').bind(null, client, logger),
getAwsAuthToken: require('./lib/get-aws-sts-token').bind(null, logger, createHash, retrieveHash),
getTtsVoices: require('./lib/get-tts-voices').bind(null, client, createHash, retrieveHash, logger),
};
};
+60
View File
@@ -0,0 +1,60 @@
const fs = require('fs/promises');
const {noopLogger, makeSynthKey} = require('./utils');
const {JAMBONES_TTS_CACHE_DURATION_MINS} = require('./config');
const EXPIRES = JAMBONES_TTS_CACHE_DURATION_MINS;
function getExtensionAndSampleRate(path) {
const match = path.match(/\.([^.]*)$/);
if (!match) {
//default should be wav file.
return ['wav', 8000];
}
const extension = match[1];
const sampleRateMap = {
r8: 8000,
r16: 16000,
r24: 24000,
r44: 44100,
r48: 48000,
r96: 96000,
};
const sampleRate = sampleRateMap[extension] || 8000;
return [extension, sampleRate];
}
async function addFileToCache(client, logger, path,
{account_sid, vendor, language, voice, deploymentId, engine, model, text}) {
let key;
logger = logger || noopLogger;
try {
key = makeSynthKey({
account_sid,
vendor,
language: language || '',
voice: voice || deploymentId,
engine,
model,
text,
});
const [extension, sampleRate] = getExtensionAndSampleRate(path);
const audioBuffer = await fs.readFile(path);
await client.setex(key, EXPIRES, JSON.stringify(
{
audioContent: audioBuffer.toString('base64'),
extension,
sampleRate
}
));
} catch (err) {
logger.error(err, 'addFileToCache: Error');
return;
}
logger.debug(`addFileToCache: added ${path} to cache with key ${key}`);
return key;
}
module.exports = addFileToCache;
+25
View File
@@ -0,0 +1,25 @@
const JAMBONES_TTS_TRIM_SILENCE = process.env.JAMBONES_TTS_TRIM_SILENCE;
const JAMBONES_DISABLE_TTS_STREAMING = process.env.JAMBONES_DISABLE_TTS_STREAMING;
const JAMBONES_DISABLE_AZURE_TTS_STREAMING = process.env.JAMBONES_DISABLE_AZURE_TTS_STREAMING;
const JAMBONES_EAGERLY_PRE_CACHE_AUDIO = process.env.JAMBONES_EAGERLY_PRE_CACHE_AUDIO;
const JAMBONES_HTTP_PROXY_IP = process.env.JAMBONES_HTTP_PROXY_IP;
const JAMBONES_HTTP_PROXY_PORT = process.env.JAMBONES_HTTP_PROXY_PORT;
const JAMBONES_TTS_CACHE_DURATION_MINS =
(parseInt(process.env.JAMBONES_TTS_CACHE_DURATION_MINS) || 4 * 60) * 60; // cache tts for 4 hours
const TMP_FOLDER = '/tmp';
const HTTP_TIMEOUT = 5000;
module.exports = {
JAMBONES_TTS_TRIM_SILENCE,
JAMBONES_DISABLE_TTS_STREAMING,
JAMBONES_DISABLE_AZURE_TTS_STREAMING,
JAMBONES_HTTP_PROXY_IP,
JAMBONES_HTTP_PROXY_PORT,
JAMBONES_TTS_CACHE_DURATION_MINS,
JAMBONES_EAGERLY_PRE_CACHE_AUDIO,
TMP_FOLDER,
HTTP_TIMEOUT
};
+78
View File
@@ -0,0 +1,78 @@
const { STSClient, GetSessionTokenCommand, AssumeRoleCommand } = require('@aws-sdk/client-sts');
const {makeAwsKey, noopLogger} = require('./utils');
const debug = require('debug')('jambonz:speech-utils');
const EXPIRY = process.env.AWS_STS_SESSION_DURATION || 3600;
// by default reset aws session before expiry time 10 mins
const CACHE_EXPIRY = process.env.AWS_STS_SESSION_RESET_EXPIRY || (EXPIRY - 600);
async function getAwsAuthToken(
logger, createHash, retrieveHash,
{speech_credential_sid, accessKeyId, secretAccessKey, region, roleArn}) {
logger = logger || noopLogger;
try {
// if incase instance profile is used, speech_credential_sid will be used as key to lookup cache
const key = makeAwsKey(roleArn || accessKeyId || speech_credential_sid);
const obj = await retrieveHash(key);
if (obj) return {...obj, servedFromCache: true};
/* access token not found in cache, so generate it using STS */
let data;
let expiry = CACHE_EXPIRY;
if (roleArn) {
const stsClient = new STSClient({ region });
const roleToAssume = { RoleArn: roleArn, RoleSessionName: 'Jambonz_Speech', DurationSeconds: EXPIRY};
const command = new AssumeRoleCommand(roleToAssume);
data = await stsClient.send(command);
} else if (accessKeyId) {
const stsClient = new STSClient({
region,
credentials: {
accessKeyId,
secretAccessKey,
}
});
const command = new GetSessionTokenCommand({DurationSeconds: EXPIRY});
data = await stsClient.send(command);
} else {
// instance profile is used.
const stsClient = new STSClient({ region });
const cred = await stsClient.config.credentials();
// method in the AWS SDK automatically fetches credentials using the default credential
// provider chain. If the credentials come from an instance profile or an environment
// variable, their expiration is controlled by AWS and not explicitly by our code.
if (cred && cred.expiration) {
const currentTime = new Date();
const expiryTime = new Date(cred.expiration);
const remainingTimeInSeconds = Math.round((expiryTime - currentTime) / 1000);
expiry = remainingTimeInSeconds;
}
data = {
Credentials: {
AccessKeyId: cred.accessKeyId,
SecretAccessKey: cred.secretAccessKey,
SessionToken: cred.sessionToken
}
};
}
const credentials = {
accessKeyId: data.Credentials.AccessKeyId,
secretAccessKey: data.Credentials.SecretAccessKey,
sessionToken: data.Credentials.SessionToken,
securityToken: data.Credentials.SessionToken
};
// Only cache if expiry is good
if (expiry > 0) {
createHash(key, credentials, expiry)
.catch((err) => logger.error(err, `Error saving hash for key ${key}`));
}
return {...credentials, servedFromCache: false};
} catch (err) {
debug(err, 'getAwsAuthToken: Error retrieving AWS auth token');
logger.error(err, 'getAwsAuthToken: Error retrieving AWS auth token');
throw err;
}
}
module.exports = getAwsAuthToken;
+2 -2
View File
@@ -2,14 +2,14 @@ const formurlencoded = require('form-urlencoded');
const {Pool} = require('undici');
const pool = new Pool('https://iam.cloud.ibm.com');
const {makeIbmKey, noopLogger} = require('./utils');
const { HTTP_TIMEOUT } = require('./config');
const debug = require('debug')('jambonz:realtimedb-helpers');
const HTTP_TIMEOUT = 5000;
async function getIbmAccessToken(client, logger, apiKey) {
logger = logger || noopLogger;
try {
const key = makeIbmKey(apiKey);
const access_token = await client.getAsync(key);
const access_token = await client.get(key);
if (access_token) return {access_token, servedFromCache: true};
/* access token not found in cache, so fetch it from Ibm */
+2 -2
View File
@@ -2,14 +2,14 @@ const formurlencoded = require('form-urlencoded');
const {Pool} = require('undici');
const pool = new Pool('https://auth.crt.nuance.com');
const {makeNuanceKey, makeBasicAuthHeader, noopLogger} = require('./utils');
const { HTTP_TIMEOUT } = require('./config');
const debug = require('debug')('jambonz:realtimedb-helpers');
const HTTP_TIMEOUT = 5000;
async function getNuanceAccessToken(client, logger, clientId, secret, scope) {
logger = logger || noopLogger;
try {
const key = makeNuanceKey(clientId, secret, scope);
const access_token = await client.getAsync(key);
const access_token = await client.get(key);
if (access_token) return {access_token, servedFromCache: true};
/* access token not found in cache, so fetch it from Nuance */
+11
View File
@@ -0,0 +1,11 @@
async function getTtsSize(client, logger, pattern = null) {
let keys;
if (pattern) {
keys = await client.keys(pattern);
} else {
keys = await client.keys('tts:*');
}
return keys.length;
}
module.exports = getTtsSize;
+55 -13
View File
@@ -1,11 +1,16 @@
const assert = require('assert');
const {noopLogger, createNuanceClient, createKryptonClient} = require('./utils');
const getNuanceAccessToken = require('./get-nuance-access-token');
const getVerbioAccessToken = require('./get-verbio-token');
const {GetVoicesRequest, Voice} = require('../stubs/nuance/synthesizer_pb');
const TextToSpeechV1 = require('ibm-watson/text-to-speech/v1');
const { IamAuthenticator } = require('ibm-watson/auth');
const ttsGoogle = require('@google-cloud/text-to-speech');
const { PollyClient, DescribeVoicesCommand } = require('@aws-sdk/client-polly');
const getAwsAuthToken = require('./get-aws-sts-token');
const {Pool} = require('undici');
const { HTTP_TIMEOUT } = require('./config');
const verbioVoicePool = new Pool('https://us.rest.speechcenter.verbio.com');
const getIbmVoices = async(client, logger, credentials) => {
const {tts_region, tts_api_key} = credentials;
@@ -87,17 +92,32 @@ const getGoogleVoices = async(_client, logger, credentials) => {
return await client.listVoices();
};
const getAwsVoices = async(_client, logger, credentials) => {
const getAwsVoices = async(_client, createHash, retrieveHash, logger, credentials) => {
try {
const {region, accessKeyId, secretAccessKey} = credentials;
const client = new PollyClient({
region,
credentials: {
accessKeyId,
secretAccessKey
}
});
const command = new DescribeVoicesCommand({LanguageCode: 'en-US'});
const {region, accessKeyId, secretAccessKey, roleArn} = credentials;
let client = null;
if (accessKeyId && secretAccessKey) {
client = new PollyClient({
region,
credentials: {
accessKeyId,
secretAccessKey
}
});
} else if (roleArn) {
client = new PollyClient({
region,
credentials: await getAwsAuthToken(
logger, createHash, retrieveHash,
{
region,
roleArn
}),
});
} else {
client = new PollyClient({region});
}
const command = new DescribeVoicesCommand({});
const response = await client.send(command);
return response;
} catch (err) {
@@ -106,6 +126,26 @@ const getAwsVoices = async(_client, logger, credentials) => {
}
};
const getVerbioVoices = async(client, logger, credentials) => {
try {
const access_token = await getVerbioAccessToken(client, logger, credentials);
const { body} = await verbioVoicePool.request({
path: '/api/v1/voices',
method: 'GET',
headers: {
'Authorization': `Bearer ${access_token.access_token}`,
'User-Agent': 'jambonz'
},
timeout: HTTP_TIMEOUT,
followRedirects: false
});
return await body.json();
} catch (err) {
logger.info({err}, 'getVerbioVoices - failed to list voices for Verbio');
throw err;
}
};
/**
* Synthesize speech to an mp3 file, and also cache the generated speech
* in redis (base64 format) for 24 hours so as to avoid unnecessarily paying
@@ -122,10 +162,10 @@ const getAwsVoices = async(_client, logger, credentials) => {
* @returns object containing filepath to an mp3 file in the /tmp folder containing
* the synthesized audio, and a variable indicating whether it was served from cache
*/
async function getTtsVoices(client, logger, {vendor, credentials}) {
async function getTtsVoices(client, createHash, retrieveHash, logger, {vendor, credentials}) {
logger = logger || noopLogger;
assert.ok(['nuance', 'ibm', 'google', 'aws', 'polly'].includes(vendor),
assert.ok(['nuance', 'ibm', 'google', 'aws', 'polly', 'verbio'].includes(vendor),
`getTtsVoices not supported for vendor ${vendor}`);
switch (vendor) {
@@ -137,7 +177,9 @@ async function getTtsVoices(client, logger, {vendor, credentials}) {
return getGoogleVoices(client, logger, credentials);
case 'aws':
case 'polly':
return getAwsVoices(client, logger, credentials);
return getAwsVoices(client, createHash, retrieveHash, logger, credentials);
case 'verbio':
return getVerbioVoices(client, logger, credentials);
default:
break;
}
+51
View File
@@ -0,0 +1,51 @@
const {Pool} = require('undici');
const { noopLogger, makeVerbioKey } = require('./utils');
const { HTTP_TIMEOUT } = require('./config');
const pool = new Pool('https://auth.speechcenter.verbio.com:444');
const debug = require('debug')('jambonz:realtimedb-helpers');
async function getVerbioAccessToken(client, logger, credentials) {
logger = logger || noopLogger;
const { client_id, client_secret } = credentials;
try {
const key = makeVerbioKey(client_id);
const access_token = await client.get(key);
if (access_token) {
return {access_token, servedFromCache: true};
}
const payload = {
client_id,
client_secret
};
const {statusCode, headers, body} = await pool.request({
path: '/api/v1/token',
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': 'jambonz'
},
body: JSON.stringify(payload),
timeout: HTTP_TIMEOUT,
followRedirects: false
});
if (200 !== statusCode) {
logger.debug({statusCode, headers, body: await body.text()}, 'error fetching access token from Verbio');
const err = new Error();
err.statusCode = statusCode;
throw err;
}
const json = await body.json();
const expiry = Math.floor(json.expiration_time - Date.now() / 1000 - 30);
await client.set(key, json.access_token, 'EX', expiry);
return {...json, servedFromCache: false};
} catch (err) {
debug(err, `getVerbioAccessToken: Error retrieving Verbio access token for client_id ${client_id}`);
logger.error(err, `getVerbioAccessToken: Error retrieving Verbio access token for client_id ${client_id}`);
throw err;
}
}
module.exports = getVerbioAccessToken;
+7 -6
View File
@@ -12,19 +12,19 @@ const debug = require('debug')('jambonz:realtimedb-helpers');
* @returns {object} result - {error, purgedCount}
*/
async function purgeTtsCache(client, logger, {all, account_sid, vendor,
language, voice, deploymentId, engine, text} = {all: true}) {
language, voice, deploymentId, engine, model, text} = {all: true}) {
logger = logger || noopLogger;
let purgedCount = 0, error;
try {
if (all) {
const keys = await client.keysAsync('tts:*');
purgedCount = await client.delAsync(keys);
const keys = await client.keys('tts:*');
purgedCount = await client.del(keys);
} else if (account_sid && !vendor && !language && !voice && !engine && !text) {
const keys = await client.keysAsync(`tts:${account_sid}:*`);
purgedCount = await client.delAsync(keys);
const keys = await client.keys(`tts:${account_sid}:*`);
purgedCount = await client.del(keys);
}
else {
const key = makeSynthKey({
@@ -33,9 +33,10 @@ async function purgeTtsCache(client, logger, {all, account_sid, vendor,
language: language || '',
voice: voice || deploymentId,
engine,
model,
text,
});
purgedCount = await client.delAsync(key);
purgedCount = await client.del(key);
if (purgedCount === 0) error = 'Specified item not found';
}
+808 -83
View File
File diff suppressed because it is too large Load Diff
+42 -6
View File
@@ -3,10 +3,10 @@ const {SynthesizerClient} = require('../stubs/nuance/synthesizer_grpc_pb');
const {RivaSpeechSynthesisClient} = require('../stubs/riva/proto/riva_tts_grpc_pb');
const {Pool} = require('undici');
const pool = new Pool('https://auth.crt.nuance.com');
const HTTP_TIMEOUT = 5000;
const NUANCE_AUTH_ENDPOINT = 'tts.api.nuance.com:443';
const grpc = require('@grpc/grpc-js');
const formurlencoded = require('form-urlencoded');
const { TMP_FOLDER, HTTP_TIMEOUT } = require('./config');
const debug = require('debug')('jambonz:realtimedb-helpers');
/**
@@ -16,12 +16,28 @@ const debug = require('debug')('jambonz:realtimedb-helpers');
*/
//const nuanceClientMap = new Map();
function makeSynthKey({account_sid = '', vendor, language, voice, engine = '', text}) {
function makeSynthKey({
account_sid = '',
vendor,
language,
voice,
engine = '',
model = '',
text
}) {
const hash = crypto.createHash('sha1');
hash.update(`${language}:${vendor}:${voice}:${engine}:${text}`);
return `tts${account_sid ? (':' + account_sid) : ''}:${hash.digest('hex')}`;
hash.update(`${language}:${vendor}:${voice}:${engine}:${model}:${text}`);
const hexHashKey = hash.digest('hex');
const accountKey = account_sid ? `:${account_sid}` : '';
const key = `tts${accountKey}:${hexHashKey}`;
return key;
}
function makeFilePath({key, salt = '', extension}) {
return `${TMP_FOLDER}/${key.replace('tts:', `tts-${salt}`)}.${extension}`;
}
const noopLogger = {
info: () => {},
debug: () => {},
@@ -43,6 +59,23 @@ function makeIbmKey(apiKey) {
return `ibm:${hash.digest('hex')}`;
}
function makeAwsKey(awsAccessKeyId) {
const hash = crypto.createHash('sha1');
hash.update(awsAccessKeyId);
return `aws:${hash.digest('hex')}`;
}
function makePlayhtKey(apiKey) {
const hash = crypto.createHash('sha1');
hash.update(apiKey);
return `playht:${hash.digest('hex')}`;
}
function makeVerbioKey(client_id) {
const hash = crypto.createHash('sha1');
hash.update(client_id);
return `verbio:${hash.digest('hex')}`;
}
function makeNuanceKey(clientId, secret, scope) {
const hash = crypto.createHash('sha1');
hash.update(`${clientId}:${secret}:${scope}`);
@@ -106,16 +139,19 @@ const createRivaClient = async(rivaUri) => {
return client;
};
module.exports = {
makeSynthKey,
makeNuanceKey,
makeIbmKey,
makePlayhtKey,
makeAwsKey,
makeVerbioKey,
getNuanceAccessToken,
createNuanceClient,
createKryptonClient,
createRivaClient,
makeBasicAuthHeader,
NUANCE_AUTH_ENDPOINT,
noopLogger
noopLogger,
makeFilePath
};
+5341 -4835
View File
File diff suppressed because it is too large Load Diff
+21 -16
View File
@@ -1,6 +1,6 @@
{
"name": "@jambonz/speech-utils",
"version": "0.0.12",
"version": "0.2.8",
"description": "TTS-related speech utilities for jambonz",
"main": "index.js",
"author": "Dave Horton",
@@ -9,10 +9,12 @@
"test": "test"
},
"scripts": {
"test": "NODE_ENV=test JAMBONES_REDIS_USERNAME=daveh JAMBONES_REDIS_PASSWORD=foobarbazzle node test/ ",
"test": "NODE_ENV=test node test/ ",
"coverage": "nyc --reporter html --report-dir ./coverage npm run test",
"jslint": "eslint index.js lib",
"build": "./build_stubs.sh"
"jslint:fix": "npm run jslint --fix",
"build": "./build_stubs.sh",
"prepare": "husky"
},
"repository": {
"type": "git",
@@ -24,25 +26,28 @@
},
"homepage": "https://github.com/jambonz/speech-utils#readme",
"dependencies": {
"@aws-sdk/client-polly": "^3.303.0",
"@google-cloud/text-to-speech": "^4.2.1",
"@grpc/grpc-js": "^1.8.13",
"@jambonz/promisify-redis": "^0.0.6",
"@aws-sdk/client-polly": "^3.496.0",
"@aws-sdk/client-sts": "^3.496.0",
"@cartesia/cartesia-js": "^2.1.0",
"@google-cloud/text-to-speech": "^5.5.0",
"@grpc/grpc-js": "^1.9.14",
"@jambonz/realtimedb-helpers": "^0.8.7",
"bent": "^7.3.12",
"debug": "^4.3.4",
"form-urlencoded": "^6.1.0",
"form-urlencoded": "^6.1.4",
"google-protobuf": "^3.21.2",
"ibm-watson": "^8.0.0",
"microsoft-cognitiveservices-speech-sdk": "^1.26.0",
"redis": "^3.1.2",
"undici": "^5.21.0"
"microsoft-cognitiveservices-speech-sdk": "1.38.0",
"openai": "^4.25.0",
"undici": "^7.5.0"
},
"devDependencies": {
"config": "^3.3.9",
"eslint": "^8.33.0",
"eslint-plugin-promise": "^6.1.1",
"config": "^3.3.11",
"eslint": "^9.3.0",
"eslint-plugin-promise": "^6.2.0",
"husky": "^9.0.11",
"nyc": "^15.1.0",
"pino": "^7.2.0",
"tape": "^5.1.1"
"pino": "^9.1.0",
"tape": "^5.7.5"
}
}
+3 -3
View File
@@ -62,9 +62,9 @@ function deserialize_nuance_tts_v1_UnarySynthesisResponse(buffer_arg) {
//
// The Synthesizer service offers these functionalities:
// - GetVoices: Queries the list of available voices, with filters to reduce the search space.
// - Synthesize: Synthesizes audio from input text and parameters, and returns an audio stream.
// - UnarySynthesize: Synthesizes audio from input text and parameters, and returns a single audio response.
// - GetVoices: Queries the list of available voices, with filters to reduce the search space.
// - Synthesize: Synthesizes audio from input text and parameters, and returns an audio stream.
// - UnarySynthesize: Synthesizes audio from input text and parameters, and returns a single audio response.
var SynthesizerService = exports.SynthesizerService = {
getVoices: {
path: '/nuance.tts.v1.Synthesizer/GetVoices',
+1 -1
View File
@@ -1 +1 @@
// GENERATED CODE -- NO SERVICES IN PROTO
// GENERATED CODE -- NO SERVICES IN PROTO
+5 -5
View File
@@ -57,7 +57,7 @@ function deserialize_nvidia_riva_tts_SynthesizeSpeechResponse(buffer_arg) {
var RivaSpeechSynthesisService = exports.RivaSpeechSynthesisService = {
// Used to request text-to-speech from the service. Submit a request containing the
// desired text and configuration, and receive audio bytes in the requested format.
synthesize: {
synthesize: {
path: '/nvidia.riva.tts.RivaSpeechSynthesis/Synthesize',
requestStream: false,
responseStream: false,
@@ -69,9 +69,9 @@ synthesize: {
responseDeserialize: deserialize_nvidia_riva_tts_SynthesizeSpeechResponse,
},
// Used to request text-to-speech returned via stream as it becomes available.
// Submit a SynthesizeSpeechRequest with desired text and configuration,
// and receive stream of bytes in the requested format.
synthesizeOnline: {
// Submit a SynthesizeSpeechRequest with desired text and configuration,
// and receive stream of bytes in the requested format.
synthesizeOnline: {
path: '/nvidia.riva.tts.RivaSpeechSynthesis/SynthesizeOnline',
requestStream: false,
responseStream: true,
@@ -83,7 +83,7 @@ synthesizeOnline: {
responseDeserialize: deserialize_nvidia_riva_tts_SynthesizeSpeechResponse,
},
// Enables clients to request the configuration of the current Synthesize service, or a specific model within the service.
getRivaSynthesisConfig: {
getRivaSynthesisConfig: {
path: '/nvidia.riva.tts.RivaSpeechSynthesis/GetRivaSynthesisConfig',
requestStream: false,
responseStream: false,
+48
View File
@@ -0,0 +1,48 @@
const test = require('tape').test ;
const config = require('config');
const opts = config.get('redis');
const logger = require('pino')({level: 'error'});
process.on('unhandledRejection', (reason, p) => {
console.log('Unhandled Rejection at: Promise', p, 'reason:', reason);
});
const sleep = (ms) => new Promise((resolve) => setTimeout(resolve, ms));
test('AWS - create and cache auth token', async(t) => {
const fn = require('..');
const {client, getAwsAuthToken} = fn(opts, logger);
if (!process.env.AWS_ACCESS_KEY_ID || !process.env.AWS_SECRET_ACCESS_KEY || !process.env.AWS_REGION) {
t.pass('skipping AWS auth token tests since no AWS credentials provided');
t.end();
client.quit();
return;
}
try {
let obj = await getAwsAuthToken({
accessKeyId: process.env.AWS_ACCESS_KEY_ID,
secretAccessKey: process.env.AWS_SECRET_ACCESS_KEY,
region: process.env.AWS_REGION
});
//console.log({obj}, 'received auth token from AWS');
t.ok(obj.securityToken && !obj.servedFromCache, 'successfullY generated auth token from AWS');
await sleep(250);
obj = await getAwsAuthToken({
accessKeyId: process.env.AWS_ACCESS_KEY_ID,
secretAccessKey: process.env.AWS_SECRET_ACCESS_KEY,
region: process.env.AWS_REGION
});
//console.log({obj}, 'received auth token from AWS - second request');
t.ok(obj.securityToken && obj.servedFromCache, 'successfully received access token from cache');
await client.flushall();
t.end();
}
catch (err) {
console.error(err);
t.end(err);
}
client.quit();
});
+2 -2
View File
@@ -31,7 +31,7 @@ test('IBM - create access key', async(t) => {
//console.log({obj}, 'received access token from IBM - second request');
t.ok(obj.access_token && obj.servedFromCache, 'successfully received access token from cache');
await client.flushallAsync();
await client.flushall();
t.end();
}
catch (err) {
@@ -65,7 +65,7 @@ test('IBM - retrieve tts voices test', async(t) => {
t.ok(voices.length > 0 && voices[0].language,
`GetVoices: successfully retrieved ${voices.length} voices from IBM`);
await client.flushallAsync();
await client.flushall();
t.end();
+3
View File
@@ -1,4 +1,7 @@
require('./docker_start');
require('./synth');
require('./list-voices');
require('./aws');
require('./ibm');
require('./nuance');
require('./docker_stop');
+32 -6
View File
@@ -12,6 +12,32 @@ const stats = {
histogram: () => {}
};
test('Verbio - get Access key and voices', async(t) => {
const fn = require('..');
const {client, getTtsVoices, getVerbioAccessToken} = fn(opts, logger);
if (!process.env.VERBIO_CLIENT_ID || !process.env.VERBIO_CLIENT_SECRET) {
t.pass('skipping Verbio test since no Verbio Keys provided');
t.end();
client.quit();
return;
}
try {
const credentials = {
client_id: process.env.VERBIO_CLIENT_ID,
client_secret: process.env.VERBIO_CLIENT_SECRET
};
let obj = await getVerbioAccessToken(credentials);
t.ok(obj.access_token , 'successfully received access token not from cache');
const voices = await getTtsVoices({vendor: 'verbio', credentials});
t.ok(voices && voices.length != 0, 'successfully received verbio voices');
} catch (err) {
console.error(err);
t.end(err);
}
client.quit();
});
test('IBM - create access key', async(t) => {
const fn = require('..');
const {client, getIbmAccessToken} = fn(opts, logger);
@@ -31,7 +57,7 @@ test('IBM - create access key', async(t) => {
//console.log({obj}, 'received access token from IBM - second request');
t.ok(obj.access_token && obj.servedFromCache, 'successfully received access token from cache');
await client.flushallAsync();
await client.flushall();
t.end();
}
catch (err) {
@@ -65,7 +91,7 @@ test('IBM - retrieve tts voices test', async(t) => {
t.ok(voices.length > 0 && voices[0].language,
`GetVoices: successfully retrieved ${voices.length} voices from IBM`);
await client.flushallAsync();
await client.flushall();
t.end();
@@ -99,7 +125,7 @@ test('Nuance hosted tests', async(t) => {
t.ok(voices.length > 0 && voices[0].language,
`GetVoices: successfully retrieved ${voices.length} voices from Nuance`);
await client.flushallAsync();
await client.flushall();
t.end();
@@ -132,7 +158,7 @@ test('Nuance on-prem tests', async(t) => {
t.ok(voices.length > 0 && voices[0].language,
`GetVoices: successfully retrieved ${voices.length} voices from Nuance`);
await client.flushallAsync();
await client.flushall();
t.end();
@@ -162,7 +188,7 @@ test('Google tests', async(t) => {
let result = await getTtsVoices(opts);
t.ok(result[0].voices.length > 0, `GetVoices: successfully retrieved ${result[0].voices.length} voices from Google`);
await client.flushallAsync();
await client.flushall();
t.end();
}
@@ -193,7 +219,7 @@ test('AWS tests', async(t) => {
let result = await getTtsVoices(opts);
t.ok(result?.Voices?.length > 0, `GetVoices: successfully retrieved ${result.Voices.length} voices from AWS`);
await client.flushallAsync();
await client.flushall();
t.end();
}
+2 -2
View File
@@ -34,7 +34,7 @@ test('Nuance hosted tests', async(t) => {
t.ok(voices.length > 0 && voices[0].language,
`GetVoices: successfully retrieved ${voices.length} voices from Nuance`);
await client.flushallAsync();
await client.flushall();
t.end();
@@ -67,7 +67,7 @@ test('Nuance on-prem tests', async(t) => {
t.ok(voices.length > 0 && voices[0].language,
`GetVoices: successfully retrieved ${voices.length} voices from Nuance`);
await client.flushallAsync();
await client.flushall();
t.end();
+85
View File
@@ -0,0 +1,85 @@
#
# Recommended minimum configuration:
#
# Example rule allowing access from your local networks.
# Adapt to list your (internal) IP networks from where browsing
# should be allowed
acl localnet src 0.0.0.1-0.255.255.255 # RFC 1122 "this" network (LAN)
acl localnet src 10.0.0.0/8 # RFC 1918 local private network (LAN)
acl localnet src 100.64.0.0/10 # RFC 6598 shared address space (CGN)
acl localnet src 169.254.0.0/16 # RFC 3927 link-local (directly plugged) machines
acl localnet src 172.16.0.0/12 # RFC 1918 local private network (LAN)
acl localnet src 192.168.0.0/16 # RFC 1918 local private network (LAN)
acl localnet src fc00::/7 # RFC 4193 local private network range
acl localnet src fe80::/10 # RFC 4291 link-local (directly plugged) machines
acl SSL_ports port 443
acl Safe_ports port 80 # http
acl Safe_ports port 21 # ftp
acl Safe_ports port 443 # https
acl Safe_ports port 70 # gopher
acl Safe_ports port 210 # wais
acl Safe_ports port 1025-65535 # unregistered ports
acl Safe_ports port 280 # http-mgmt
acl Safe_ports port 488 # gss-http
acl Safe_ports port 591 # filemaker
acl Safe_ports port 777 # multiling http
#
# Recommended minimum Access Permission configuration:
#
# Deny requests to certain unsafe ports
http_access deny !Safe_ports
# Deny CONNECT to other than secure SSL ports
http_access allow CONNECT !SSL_ports
# Only allow cachemgr access from localhost
http_access allow localhost manager
http_access deny manager
# This default configuration only allows localhost requests because a more
# permissive Squid installation could introduce new attack vectors into the
# network by proxying external TCP connections to unprotected services.
http_access allow localhost
# The two deny rules below are unnecessary in this default configuration
# because they are followed by a "deny all" rule. However, they may become
# critically important when you start allowing external requests below them.
# Protect web applications running on the same server as Squid. They often
# assume that only local users can access them at "localhost" ports.
http_access deny to_localhost
# Protect cloud servers that provide local users with sensitive info about
# their server via certain well-known link-local (a.k.a. APIPA) addresses.
http_access deny to_linklocal
#
# INSERT YOUR OWN RULE(S) HERE TO ALLOW ACCESS FROM YOUR CLIENTS
#
# For example, to allow access from your local networks, you may uncomment the
# following rule (and/or add rules that match your definition of "local"):
# http_access allow localnet
# And finally deny all other access to this proxy
http_access deny all
# Squid normally listens to port 3128
http_port 3128
# Uncomment and adjust the following to add a disk cache directory.
#cache_dir ufs /usr/local/var/cache/squid 100 16 256
# Leave coredumps in the first cache dir
coredump_dir /usr/local/var/cache/squid
#
# Add any of your own refresh_pattern entries above these.
#
refresh_pattern ^ftp: 1440 20% 10080
refresh_pattern ^gopher: 1440 0% 1440
refresh_pattern -i (/cgi-bin/|\?) 0 0% 0
refresh_pattern . 0 20% 4320
+494 -21
View File
@@ -5,7 +5,7 @@ const fs = require('fs');
const {makeSynthKey} = require('../lib/utils');
const logger = require('pino')();
const bent = require('bent');
const getJSON = bent('json')
const getJSON = bent('json');
process.on('unhandledRejection', (reason, p) => {
console.log('Unhandled Rejection at: Promise', p, 'reason:', reason);
@@ -20,7 +20,7 @@ const stats = {
test('Google speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
const {synthAudio, addFileToCache, client} = fn(opts, logger);
if (!process.env.GCP_FILE && !process.env.GCP_JSON_KEY) {
t.pass('skipping google speech synth tests since neither GCP_FILE nor GCP_JSON_KEY provided');
@@ -38,7 +38,7 @@ test('Google speech synth tests', async(t) => {
},
},
language: 'en-GB',
gender: 'MALE',
gender: 'FEMALE',
text: 'This is a test. This is only a test',
salt: 'foo.bar',
});
@@ -53,11 +53,19 @@ test('Google speech synth tests', async(t) => {
},
},
language: 'en-GB',
gender: 'MALE',
gender: 'FEMALE',
text: 'This is a test. This is only a test',
});
t.ok(opts.servedFromCache, `successfully retrieved cached google audio from ${opts.filePath}`);
const success = await addFileToCache(opts.filePath, {
vendor: 'google',
language: 'en-GB',
gender: 'FEMALE',
text: 'This is a test. This is only a test'
});
t.ok(success, `successfully added ${opts.filePath} to cache`);
opts = await synthAudio(stats, {
vendor: 'google',
credentials: {
@@ -68,7 +76,7 @@ test('Google speech synth tests', async(t) => {
},
disableTtsCache: true,
language: 'en-GB',
gender: 'MALE',
gender: 'FEMALE',
text: 'This is a test. This is only a test',
});
t.ok(!opts.servedFromCache, `successfully synthesized google audio regardless of current cache to ${opts.filePath}`);
@@ -79,6 +87,85 @@ test('Google speech synth tests', async(t) => {
client.quit();
});
test('Google speech Custom voice synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.GCP_CUSTOM_VOICE_FILE &&
!process.env.GCP_CUSTOM_VOICE_JSON_KEY ||
!process.env.GCP_CUSTOM_VOICE_MODEL) {
t.pass(`skipping google speech synth tests since neither
GCP_CUSTOM_VOICE_FILE nor GCP_CUSTOM_VOICE_JSON_KEY provided, GCP_CUSTOM_VOICE_MODEL is not provided`);
return t.end();
}
try {
const str = process.env.GCP_CUSTOM_VOICE_JSON_KEY || fs.readFileSync(process.env.GCP_CUSTOM_VOICE_FILE);
const creds = JSON.parse(str);
const opts = await synthAudio(stats, {
vendor: 'google',
credentials: {
credentials: {
client_email: creds.client_email,
private_key: creds.private_key,
},
},
language: 'en-AU',
text: 'This is a test. This is only a test',
voice: {
reportedUsage: 'REALTIME',
model: process.env.GCP_CUSTOM_VOICE_MODEL
}
});
t.ok(!opts.servedFromCache, `successfully synthesized google custom voice audio to ${opts.filePath}`);
} catch (err) {
console.error(err);
t.end(err);
}
client.quit();
});
test('Google speech voice cloning synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.GCP_CUSTOM_VOICE_FILE &&
!process.env.GCP_CUSTOM_VOICE_JSON_KEY ||
!process.env.GCP_VOICE_CLONING_FILE &&
!process.env.GCP_VOICE_CLONING_JSON_KEY) {
t.pass(`skipping google speech synth tests since neither
GCP_CUSTOM_VOICE_FILE nor GCP_CUSTOM_VOICE_JSON_KEY provided,
GCP_VOICE_CLONING_FILE nor GCP_VOICE_CLONING_JSON_KEY is not provided`);
return t.end();
}
try {
const googleKey = process.env.GCP_CUSTOM_VOICE_JSON_KEY ||
fs.readFileSync(process.env.GCP_CUSTOM_VOICE_FILE);
const voice_cloning_key = process.env.GCP_VOICE_CLONING_JSON_KEY ||
fs.readFileSync(process.env.GCP_VOICE_CLONING_FILE).toString();
const creds = JSON.parse(googleKey);
const opts = await synthAudio(stats, {
vendor: 'google',
credentials: {
credentials: {
client_email: creds.client_email,
private_key: creds.private_key,
project_id: creds.project_id
},
},
language: 'en-US',
text: 'This is a test. This is only a test. This is a test. This is only a test. This is a test. This is only a test',
voice: {
voice_cloning_key
}
});
t.ok(!opts.servedFromCache, `successfully synthesized google voice cloning audio to ${opts.filePath}`);
} catch (err) {
console.error(err);
t.end(err);
}
client.quit();
});
test('AWS speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
@@ -120,6 +207,33 @@ test('AWS speech synth tests', async(t) => {
client.quit();
});
test('AWS speech synth tests by RoleArn', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.AWS_ROLE_ARN || !process.env.AWS_REGION) {
t.pass('skipping AWS speech synth tests by RoleArn since AWS_ROLE_ARN or AWS_REGION not provided');
return t.end();
}
try {
let opts = await synthAudio(stats, {
vendor: 'aws',
credentials: {
roleArn: process.env.AWS_ROLE_ARN,
region: process.env.AWS_REGION,
},
language: 'en-US',
voice: 'Joey',
text: 'This is a test. This is only a test',
});
t.ok(!opts.servedFromCache, `successfully synthesized aws by roleArn audio to ${opts.filePath}`);
} catch (err) {
console.error(err);
t.end(err);
}
client.quit();
});
test('Azure speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
@@ -146,9 +260,12 @@ test('Azure speech synth tests', async(t) => {
language: 'en-US',
voice: 'en-US-ChristopherNeural',
text: longText,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized microsoft audio to ${opts.filePath}`);
if (process.env.JAMBONES_HTTP_PROXY_IP && process.env.JAMBONES_HTTP_PROXY_PORT) {
t.pass('successfully used proxy to reach microsoft tts service');
}
opts = await synthAudio(stats, {
vendor: 'microsoft',
@@ -159,6 +276,7 @@ test('Azure speech synth tests', async(t) => {
language: 'en-US',
voice: 'en-US-ChristopherNeural',
text: longText,
renderForCaching: true
});
t.ok(opts.servedFromCache, `successfully retrieved microsoft audio from cache ${opts.filePath}`);
} catch (err) {
@@ -168,6 +286,58 @@ test('Azure speech synth tests', async(t) => {
client.quit();
});
test('Azure SSML tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.MICROSOFT_API_KEY || !process.env.MICROSOFT_REGION) {
t.pass('skipping Microsoft speech synth tests since MICROSOFT_API_KEY or MICROSOFT_REGION not provided');
return t.end();
}
try {
const text = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="en-US">
<voice name="en-US-JennyMultilingualNeural">
<mstts:express-as style="cheerful" styledegree="2">That'd be just amazing!
</mstts:express-as>
</voice>
</speak>`;
let opts = await synthAudio(stats, {
vendor: 'microsoft',
credentials: {
api_key: process.env.MICROSOFT_API_KEY,
region: process.env.MICROSOFT_REGION,
},
language: 'en-US',
voice: 'en-US-ChristopherNeural',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized microsoft audio to ${opts.filePath}`);
if (process.env.JAMBONES_HTTP_PROXY_IP && process.env.JAMBONES_HTTP_PROXY_PORT) {
t.pass('successfully used proxy to reach microsoft tts service');
}
opts = await synthAudio(stats, {
vendor: 'microsoft',
credentials: {
api_key: process.env.MICROSOFT_API_KEY,
region: process.env.MICROSOFT_REGION,
},
language: 'en-US',
voice: 'en-US-ChristopherNeural',
text,
renderForCaching: true
});
t.ok(opts.servedFromCache, `successfully retrieved microsoft audio from cache ${opts.filePath}`);
} catch (err) {
console.error(err);
t.end(err);
}
client.quit();
});
test('Azure custom voice speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
@@ -189,6 +359,7 @@ test('Azure custom voice speech synth tests', async(t) => {
language: 'en-US',
voice: process.env.MICROSOFT_CUSTOM_VOICE,
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized microsoft audio to ${opts.filePath}`);
@@ -203,6 +374,7 @@ test('Azure custom voice speech synth tests', async(t) => {
language: 'en-US',
voice: process.env.MICROSOFT_CUSTOM_VOICE,
text,
renderForCaching: true
});
t.ok(opts.servedFromCache, `successfully retrieved microsoft custom voice audio from cache ${opts.filePath}`);
} catch (err) {
@@ -300,7 +472,7 @@ test('Nvidia speech synth tests', async(t) => {
let opts = await synthAudio(stats, {
vendor: 'nvidia',
credentials: {
riva_uri: process.env.RIVA_URI,
riva_server_uri: process.env.RIVA_URI,
},
language: 'en-US',
voice: 'English-US.Female-1',
@@ -311,7 +483,7 @@ test('Nvidia speech synth tests', async(t) => {
opts = await synthAudio(stats, {
vendor: 'nvidia',
credentials: {
riva_uri: process.env.RIVA_URI,
riva_server_uri: process.env.RIVA_URI,
},
language: 'en-US',
voice: 'English-US.Female-1',
@@ -382,6 +554,7 @@ test('Custom Vendor speech synth tests', async(t) => {
text: 'This is a test. This is only a test',
});
t.ok(!opts.servedFromCache, `successfully synthesized custom vendor audio to ${opts.filePath}`);
t.ok(opts.filePath.endsWith('wav'), 'audio is cached as wav file');
let obj = await getJSON(`http://127.0.0.1:3100/lastRequest/somethingnew`);
t.ok(obj.headers.Authorization == 'Bearer some_jwt_token', 'Custom Vendor Authentication Header is correct');
t.ok(obj.body.language == 'en-US', 'Custom Vendor Language is correct');
@@ -389,6 +562,21 @@ test('Custom Vendor speech synth tests', async(t) => {
t.ok(obj.body.type == 'text', 'Custom Vendor type is correct');
t.ok(obj.body.text == 'This is a test. This is only a test', 'Custom Vendor text is correct');
// Checking if cache is stored with wav format
opts = await synthAudio(stats, {
vendor: 'custom:somethingnew',
credentials: {
use_for_tts: 1,
custom_tts_url: "http://127.0.0.1:3100/somethingnew",
auth_token: 'some_jwt_token'
},
language: 'en-US',
voice: 'English-US.Female-1',
text: 'This is a test. This is only a test',
});
t.ok(opts.servedFromCache, `successfully get custom vendor cached audio to ${opts.filePath}`);
t.ok(opts.filePath.endsWith('wav'), 'audio is cached as wav file');
opts = await synthAudio(stats, {
vendor: 'custom:somethingnew2',
credentials: {
@@ -411,20 +599,303 @@ test('Custom Vendor speech synth tests', async(t) => {
client.quit();
});
test('Elevenlabs speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.ELEVENLABS_API_KEY || !process.env.ELEVENLABS_VOICE_ID || !process.env.ELEVENLABS_MODEL_ID) {
t.pass('skipping ElevenLabs speech synth tests since ELEVENLABS_API_KEY or ELEVENLABS_VOICE_ID or ELEVENLABS_MODEL_ID not provided');
return t.end();
}
const text = 'Hi there and welcome to jambones!';
try {
let opts = await synthAudio(stats, {
vendor: 'elevenlabs',
credentials: {
api_key: process.env.ELEVENLABS_API_KEY,
model_id: process.env.ELEVENLABS_MODEL_ID,
options: JSON.stringify({
optimize_streaming_latency: 1,
voice_settings: {
similarity_boost: 1,
stability: 0.8,
style: 1,
use_speaker_boost: true
}
})
},
language: 'en-US',
voice: process.env.ELEVENLABS_VOICE_ID,
text,
});
t.ok(!opts.servedFromCache, `successfully synthesized eleven audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
});
const testPlayHT = async(t, voice_engine) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.PLAYHT_API_KEY || !process.env.PLAYHT_USER_ID) {
t.pass('skipping PlayHT speech synth tests since PLAYHT_API_KEY or PLAYHT_USER_ID is/are not provided');
return t.end();
}
const text = 'Hi there and welcome to jambones! ' + Date.now();
try {
const opts = await synthAudio(stats, {
vendor: 'playht',
credentials: {
api_key: process.env.PLAYHT_API_KEY,
user_id: process.env.PLAYHT_USER_ID,
voice_engine,
options: JSON.stringify({
quality: 'medium',
speed: 1,
seed: 1,
temperature: 1,
emotion: 'female_happy',
voice_guidance: 3,
style_guidance: 20,
text_guidance: 1,
})
},
language: 'english',
voice: 's3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully playht eleven audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
};
test('PlayHT speech synth tests', async(t) => {
await testPlayHT(t, 'PlayHT2.0-turbo');
});
test('PlayHT3.0 speech synth tests', async(t) => {
await testPlayHT(t, 'Play3.0');
});
test('Cartesia speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.CARTESIA_API_KEY) {
t.pass('skipping Cartesia speech synth tests since CARTESIA_API_KEY is not provided');
return t.end();
}
const text = 'Hi there and welcome to jambones! ' + Date.now();
try {
const opts = await synthAudio(stats, {
vendor: 'cartesia',
credentials: {
api_key: process.env.CARTESIA_API_KEY,
model_id: 'sonic-english',
options: JSON.stringify({
speed: 1,
emotion: 'female_happy',
})
},
language: 'en',
voice: '694f9389-aac1-45b6-b726-9d9369183238',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully playht eleven audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
});
test('rimelabs speech synth tests mist', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.RIMELABS_API_KEY) {
t.pass('skipping rimelabs speech synth tests since RIMELABS_API_KEY is not provided');
return t.end();
}
const text = 'Hi there and welcome to jambones!';
try {
const opts = await synthAudio(stats, {
vendor: 'rimelabs',
credentials: {
api_key: process.env.RIMELABS_API_KEY,
model_id: 'mist',
options: JSON.stringify({
speedAlpha: 1.0,
reduceLatency: false
})
},
language: 'eng',
voice: 'amber',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized rimelabs audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
});
test('rimelabs speech synth tests mistv2', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.RIMELABS_API_KEY) {
t.pass('skipping rimelabs speech synth tests since RIMELABS_API_KEY is not provided');
return t.end();
}
const text = 'Hi there and welcome to jambones!';
try {
const opts = await synthAudio(stats, {
vendor: 'rimelabs',
credentials: {
api_key: process.env.RIMELABS_API_KEY,
model_id: 'mistv2',
options: JSON.stringify({
speedAlpha: 1.0,
reduceLatency: false
})
},
language: 'spa',
voice: 'pablo',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized rimelabs mistv2 audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
});
test('whisper speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.OPENAI_API_KEY) {
t.pass('skipping OPENAI speech synth tests since OPENAI_API_KEY not provided');
return t.end();
}
const text = 'Hi there and welcome to jambones!';
try {
let opts = await synthAudio(stats, {
vendor: 'whisper',
credentials: {
api_key: process.env.OPENAI_API_KEY,
model_id: 'tts-1'
},
language: 'en-US',
voice: 'alloy',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized whisper audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
});
test('Verbio speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.VERBIO_CLIENT_ID || !process.env.VERBIO_CLIENT_SECRET) {
t.pass('skipping Verbio Synthesize test since no Verbio Keys provided');
t.end();
client.quit();
return;
}
const text = 'Hi there and welcome to jambones!';
try {
let opts = await synthAudio(stats, {
vendor: 'verbio',
credentials: {
client_id: process.env.VERBIO_CLIENT_ID,
client_secret: process.env.VERBIO_CLIENT_SECRET
},
language: 'en-US',
voice: 'tommy_en-us',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized whisper audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
})
test('Deepgram speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.DEEPGRAM_API_KEY) {
t.pass('skipping Deepgram speech synth tests since DEEPGRAM_API_KEY');
return t.end();
}
const text = 'Hi there and welcome to jambones!';
try {
let opts = await synthAudio(stats, {
vendor: 'deepgram',
credentials: {
api_key: process.env.DEEPGRAM_API_KEY
},
model: 'aura-asteria-en',
text,
renderForCaching: true
});
t.ok(!opts.servedFromCache, `successfully synthesized deepgram audio to ${opts.filePath}`);
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
}
client.quit();
})
test('TTS Cache tests', async(t) => {
const fn = require('..');
const {purgeTtsCache, client} = fn(opts, logger);
const {purgeTtsCache, getTtsSize, client} = fn(opts, logger);
try {
// save some random tts keys to cache
const minRecords = 8;
for (const i in Array(minRecords).fill(0)) {
await client.setAsync(makeSynthKey({vendor: i, language: i, voice: i, engine: i, text: i}), i);
await client.set(makeSynthKey({vendor: i, language: i, voice: i, engine: i, model: i, text: i}), i);
}
const count = await getTtsSize();
t.ok(count >= minRecords, 'getTtsSize worked.');
const {purgedCount} = await purgeTtsCache();
t.ok(purgedCount >= minRecords, `successfully purged at least ${minRecords} tts records from cache`);
const cached = (await client.keysAsync('tts:*')).length;
const cached = (await client.keys('tts:*')).length;
t.equal(cached, 0, `successfully purged all tts records from cache`);
} catch (err) {
@@ -435,11 +906,11 @@ test('TTS Cache tests', async(t) => {
try {
// save some random tts keys to cache
for (const i in Array(10).fill(0)) {
await client.setAsync(makeSynthKey({vendor: i, language: i, voice: i, engine: i, text: i}), i);
await client.set(makeSynthKey({vendor: i, language: i, voice: i, engine: i, text: i}), i);
}
// save a specific key to tts cache
const opts = {vendor: 'aws', language: 'en-US', voice: 'MALE', engine: 'Engine', text: 'Hello World!'};
await client.setAsync(makeSynthKey(opts), opts.text);
await client.set(makeSynthKey(opts), opts.text);
const {purgedCount} = await purgeTtsCache({all: false, ...opts});
t.ok(purgedCount === 1, `successfully purged one specific tts record from cache`);
@@ -451,13 +922,15 @@ test('TTS Cache tests', async(t) => {
language: 'non-existing',
voice: 'non-existing',
});
t.ok(purgedCountWhenErrored === 0, `purged no records when specified key was not found`);
t.ok(error, `error returned when specified key was not found`);
t.ok(purgedCountWhenErrored === 0, 'purged no records when specified key was not found');
t.ok(error, 'error returned when specified key was not found');
// make sure other tts keys are still there
const cached = (await client.keysAsync('tts:*')).length;
t.ok(cached >= 1, `successfully kept all non-specified tts records in cache`);
const cached = await client.keys('tts:*');
t.ok(cached.length >= 1, 'successfully kept all non-specified tts records in cache');
process.env.VG_TRIM_TTS_SILENCE = 'true';
await client.set(makeSynthKey({ vendor: 'azure' }), 'value');
} catch (err) {
console.error(JSON.stringify(err));
t.end(err);
@@ -471,21 +944,21 @@ test('TTS Cache tests', async(t) => {
const account_sid = "12412512_cabc_5aff"
const account_sid2 = "22412512_cabc_5aff"
for (const i in Array(minRecords).fill(0)) {
await client.setAsync(makeSynthKey({account_sid, vendor: i, language: i, voice: i, engine: i, text: i}), i);
await client.set(makeSynthKey({account_sid, vendor: i, language: i, voice: i, engine: i, text: i}), i);
}
for (const i in Array(minRecords).fill(0)) {
await client.setAsync(makeSynthKey({account_sid: account_sid2, vendor: i, language: i, voice: i, engine: i, text: i}), i);
await client.set(makeSynthKey({account_sid: account_sid2, vendor: i, language: i, voice: i, engine: i, text: i}), i);
}
const {purgedCount} = await purgeTtsCache({account_sid});
t.equal(purgedCount, minRecords, `successfully purged at least ${minRecords} tts records from cache for account_sid:${account_sid}`);
let cached = (await client.keysAsync('tts:*')).length;
let cached = (await client.keys('tts:*')).length;
t.equal(cached, minRecords, `successfully purged all tts records from cache for account_sid:${account_sid}`);
const {purgedCount: purgedCount2} = await purgeTtsCache({account_sid: account_sid2});
t.equal(purgedCount2, minRecords, `successfully purged at least ${minRecords} tts records from cache for account_sid:${account_sid2}`);
cached = (await client.keysAsync('tts:*')).length;
cached = (await client.keys('tts:*')).length;
t.equal(cached, 0, `successfully purged all tts records from cache`);
} catch (err) {