ben.carrasco/jambonz-feature-server
1
0
Fork 0
mirror of https://github.com/jambonz/jambonz-feature-server.git synced 2025-12-19 04:17:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add ability to override certain tts streaming options via the config … (#1429)

Browse Source 
* Add ability to override certain tts streaming options via the config verb.

* Update to null operator(??), support parameter override via config
This commit is contained in:
Ed Robbins
2025-11-12 13:54:01 -05:00
committed by GitHub
parent 0442144793
commit f92b1dbc97
1 changed files with 30 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
lib/tasks/tts-task.js
View File

@@ -85,55 +85,66 @@ class TtsTask extends Task {
}
async setTtsStreamingChannelVars(vendor, language, voice, credentials, ep) {
const {api_key, model_id, api_uri, custom_tts_streaming_url, auth_token} = credentials;
let obj;
const {api_key, model_id, api_uri, custom_tts_streaming_url, auth_token, options} = credentials;
// api_key, model_id, api_uri, custom_tts_streaming_url, and auth_token are encoded in the credentials
// allow them to be overriden via config, using options
// give preference to options passed in via config
const local_options = {...JSON.parse(options), ...this.options};
const local_voice_settings = {...JSON.parse(options).voice_settings, ...this.options.voice_settings};
const local_api_key = local_options.api_key ?? api_key;
const local_model_id = local_options.model_id ?? model_id;
const local_api_uri = local_options.api_uri ?? api_uri;
const local_custom_tts_streaming_url = local_options.custom_tts_streaming_url ?? custom_tts_streaming_url;
const local_auth_token = local_options.auth_token ?? auth_token;
this.logger.debug(`setTtsStreamingChannelVars: vendor: ${vendor}, language: ${language}, voice: ${voice}`);
let obj;
switch (vendor) {
case 'deepgram':
obj = {
DEEPGRAM_API_KEY: api_key,
DEEPGRAM_API_KEY: local_api_key,
DEEPGRAM_TTS_STREAMING_MODEL: voice
};
break;
case 'cartesia':
obj = {
CARTESIA_API_KEY: api_key,
CARTESIA_TTS_STREAMING_MODEL_ID: model_id,
CARTESIA_API_KEY: local_api_key,
CARTESIA_TTS_STREAMING_MODEL_ID: local_model_id,
CARTESIA_TTS_STREAMING_VOICE_ID: voice,
CARTESIA_TTS_STREAMING_LANGUAGE: language || 'en',
};
break;
case 'elevenlabs':
const {stability, similarity_boost, use_speaker_boost, style, speed} = this.options.voice_settings || {};
// eslint-disable-next-line max-len
const {stability, similarity_boost, use_speaker_boost, style, speed} = local_voice_settings || {};
obj = {
ELEVENLABS_API_KEY: api_key,
...(api_uri && {ELEVENLABS_API_URI: api_uri}),
ELEVENLABS_TTS_STREAMING_MODEL_ID: model_id,
ELEVENLABS_API_KEY: local_api_key,
...(api_uri && {ELEVENLABS_API_URI: local_api_uri}),
ELEVENLABS_TTS_STREAMING_MODEL_ID: local_model_id,
ELEVENLABS_TTS_STREAMING_VOICE_ID: voice,
// 20/12/2024 - only eleven_turbo_v2_5 support multiple language
...(['eleven_turbo_v2_5'].includes(model_id) && {ELEVENLABS_TTS_STREAMING_LANGUAGE: language}),
...(['eleven_turbo_v2_5'].includes(local_model_id) && {ELEVENLABS_TTS_STREAMING_LANGUAGE: language}),
...(stability && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_STABILITY: stability}),
...(similarity_boost && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_SIMILARITY_BOOST: similarity_boost}),
...(use_speaker_boost && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_USE_SPEAKER_BOOST: use_speaker_boost}),
...(style && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_STYLE: style}),
// speed has value 0.7 to 1.2, 1.0 is default, make sure we send the value event it's 0
...(speed !== null && speed !== undefined && {ELEVENLABS_TTS_STREAMING_VOICE_SETTINGS_SPEED: `${speed}`}),
...(this.options.pronunciation_dictionary_locators &&
Array.isArray(this.options.pronunciation_dictionary_locators) && {
...(local_options.pronunciation_dictionary_locators &&
Array.isArray(local_options.pronunciation_dictionary_locators) && {
ELEVENLABS_TTS_STREAMING_PRONUNCIATION_DICTIONARY_LOCATORS:
JSON.stringify(this.options.pronunciation_dictionary_locators)
JSON.stringify(local_options.pronunciation_dictionary_locators)
}),
};
break;
case 'rimelabs':
const {
pauseBetweenBrackets, phonemizeBetweenBrackets, inlineSpeedAlpha, speedAlpha, reduceLatency
} = this.options;
} = local_options;
obj = {
RIMELABS_API_KEY: api_key,
RIMELABS_TTS_STREAMING_MODEL_ID: model_id,
RIMELABS_API_KEY: local_api_key,
RIMELABS_TTS_STREAMING_MODEL_ID: local_model_id,
RIMELABS_TTS_STREAMING_VOICE_ID: voice,
RIMELABS_TTS_STREAMING_LANGUAGE: language || 'en',
...(pauseBetweenBrackets && {RIMELABS_TTS_STREAMING_PAUSE_BETWEEN_BRACKETS: pauseBetweenBrackets}),
@@ -148,8 +159,8 @@ class TtsTask extends Task {
if (vendor.startsWith('custom:')) {
const use_tls = custom_tts_streaming_url.startsWith('wss://');
obj = {
CUSTOM_TTS_STREAMING_HOST: custom_tts_streaming_url.replace(/^(ws|wss):\/\//, ''),
CUSTOM_TTS_STREAMING_API_KEY: auth_token,
CUSTOM_TTS_STREAMING_HOST: local_custom_tts_streaming_url.replace(/^(ws|wss):\/\//, ''),
CUSTOM_TTS_STREAMING_API_KEY: local_auth_token,
CUSTOM_TTS_STREAMING_VOICE_ID: voice,
CUSTOM_TTS_STREAMING_LANGUAGE: language || 'en',
CUSTOM_TTS_STREAMING_USE_TLS: use_tls