ben.carrasco/freeswitch-modules
1
0
Fork 0
mirror of https://github.com/jambonz/freeswitch-modules.git synced 2025-12-19 08:57:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md (#9)

Browse Source 
Updated ElevenLabs module to include an example of how to use the module as well as links to params in ElevenLabs docs.
This commit is contained in:
Lyle Pratt
2024-10-03 07:06:32 -05:00
committed by GitHub
parent f7f8f52283
commit 9f7a06ce56
1 changed files with 17 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
mod_elevenlabs_tts/README.md
View File

@@ -1,11 +1,11 @@
# mod_google_tts # mod_google_tts
A Freeswitch module that allows Google Text-to-Speech API to be used as a tts provider. A Freeswitch module that allows Eleven Labs' Text-to-Speech API to be used as a tts provider.
## API ## API
### Commands ### Commands
This freeswitch module does not add any new commands, per se. Rather, it integrates into the Freeswitch TTS interface such that it is invoked when an application uses the mod_dptools `speak` command with a tts engine of `google_tts` and a voice equal to the language code associated to one of the [supported Wavenet voices](https://cloud.google.com/text-to-speech/docs/voices) This freeswitch module does not add any new commands, per se. Rather, it integrates into the Freeswitch TTS interface such that it is invoked when an application uses the mod_dptools `speak` command with a tts engine of `elevenlabs` and a voice equal to the language code associated to one of the [supported Eleven Labs voices](https://elevenlabs.io/docs/api-reference/query-library)
### Events ### Events
None. None.
@@ -13,11 +13,19 @@ None.
## Usage ## Usage
When using [drachtio-fsrmf](https://www.npmjs.com/package/drachtio-fsmrf), you can access this functionality via the speak method on the 'endpoint' object. When using [drachtio-fsrmf](https://www.npmjs.com/package/drachtio-fsmrf), you can access this functionality via the speak method on the 'endpoint' object.
```js ```js
ep.speak({ var text = "Hello World";
ttsEngine: 'google_tts', await endpoint.speak({
voice: 'en-GB-Wavenet-A', "ttsEngine": 'elevenlabs',
text: 'This aggression will not stand' "voice": "W9OIfHh5DtdYiZUcFiql",
}); "text": `{use_speaker_boost=1,optimize_streaming_latency=4,style=0.5,stability=0.5,similarity_boost=0.75,api_key=XXYYZZ,model_id=eleven_turbo_v2}${text}`,
});
``` ```
## Examples ## Options
[google_tts.js](../../examples/google_tts.js)
Documentation on these options can be found in Eleven Labs API docs: [Voice Settings](https://elevenlabs.io/docs/speech-synthesis/voice-settings)
- use_speaker_boost
- optimize_streaming_latency
- style
- stability
- similarity_boost