SillyTavern/public/scripts/extensions/tts
Cohee be2d658a2e Update TTS extension to use new popup 2024-06-30 22:01:34 +03:00
..
alltalk.js Lint and clean-up 2024-04-15 00:39:15 +03:00
azure.js Update TTS extension to use new popup 2024-06-30 22:01:34 +03:00
coqui.js Update TTS extension to use new popup 2024-06-30 22:01:34 +03:00
coqui_api_models_settings.json Updated RVC UI to allow per characters settings without manual voice map text. 2023-08-15 21:15:31 +02:00
coqui_api_models_settings_full.json Added full coqui-api model list available via new origin in Coqui UI: Coqui API (Experimental). Some model might not work, need to be tested. 2023-08-17 21:33:06 +02:00
edge.js Fix TTS audio preview 2024-06-17 20:28:19 +03:00
elevenlabs.js Fix elevenlabs v2 settings 2024-06-09 21:04:35 +03:00
gsvi.js Clean-up labels 2024-05-18 20:03:02 +03:00
index.js Force reinitialize when chat changed 2024-06-30 14:06:31 +03:00
manifest.json Added Coqui TTS extension option to use local models (no language/no speakers) 2023-08-16 19:19:13 +02:00
novel.js Update TTS extension to use new popup 2024-06-30 22:01:34 +03:00
openai.js Adjust step for OAI TTS speed 2023-12-16 01:58:52 +02:00
readme.md Add provider-specific TTS processing: XTTS - replace ellipsis, Novel - remove tildes. 2023-11-27 13:25:49 +02:00
sbvits2.js rejoin style 2024-06-25 20:05:41 +09:00
settings.html Move TTS settings to HTML template 2024-06-24 22:19:21 +03:00
silerotts.js Replace quote extract separator for Silero TTS 2024-03-14 14:56:58 +02:00
speecht5.js Fix TTS audio preview 2024-06-17 20:28:19 +03:00
style.css Clean-up wand menu styles 2024-06-24 23:32:24 +03:00
system.js lint: Require semicolons 2023-12-02 21:11:06 +02:00
vits.js TTS: Add support for VITS/W2V2-VITS/Bert-VITS2 (#2439) 2024-06-29 14:15:37 +03:00
xtts.js Fix settings UI loading 2024-01-03 21:35:04 +02:00

readme.md

Provider Requirements.

Because I don't know how, or if you can, and/or maybe I am just too lazy to implement interfaces in JS, here's the requirements of a provider that the extension needs to operate.

class YourTtsProvider

Required

Exported for use in extension index.js, and added to providers list in index.js

  1. generateTts(text, voiceId)
  2. fetchTtsVoiceObjects()
  3. onRefreshClick()
  4. checkReady()
  5. loadSettings(settingsObject)
  6. settings field
  7. settingsHtml field

Optional

  1. previewTtsVoice()
  2. separator field
  3. processText(text)

Requirement Descriptions

generateTts(text, voiceId)

Must return audioData.type in ['audio/mpeg', 'audio/wav', 'audio/x-wav', 'audio/wave', 'audio/webm'] Must take text to be rendered and the voiceId to identify the voice to be used

fetchTtsVoiceObjects()

Required. Used by the TTS extension to get a list of voice objects from the provider. Must return an list of voice objects representing the available voices.

  1. name: a friendly user facing name to assign to characters. Shows in dropdown list next to user.
  2. voice_id: the provider specific id of the voice used in fetchTtsGeneration() call
  3. preview_url: a URL to a local audio file that will be used to sample voices
  4. lang: OPTIONAL language string

getVoice(voiceName)

Required. Must return a single voice object matching the provided voiceName. The voice object must have the following at least:

  1. name: a friendly user facing name to assign to characters. Shows in dropdown list next to user.
  2. voice_id: the provider specific id of the voice used in fetchTtsGeneration() call
  3. preview_url: a URL to a local audio file that will be used to sample voices
  4. lang: OPTIONAL language indicator

onRefreshClick()

Required. Users click this button to reconnect/reinit the selected provider. Responds to the user clicking the refresh button, which is intended to re-initialize the Provider into a working state, like retrying connections or checking if everything is loaded.

checkReady()

Required. Return without error to let TTS extension know that the provider is ready. Return an error to block the main TTS extension for initializing the provider and UI. The error will be put in the TTS extension UI directly.

loadSettings(settingsObject)

Required. Handle the input settings from the TTS extension on provider load. Put code in here to load your provider settings.

settings field

Required, used for storing any provider state that needs to be saved. Anything stored in this field is automatically persisted under extension_settings[providerName] by the main extension in saveTtsProviderSettings(), as well as loaded when the provider is selected in loadTtsProvider(provider). TTS extension doesn't expect any specific contents.

settingsHtml field

Required, injected into the TTS extension UI. Besides adding it, not relied on by TTS extension directly.

previewTtsVoice()

Optional. Function to handle playing previews of voice samples if no direct preview_url is available in fetchTtsVoiceObjects() response

separator field

Optional. Used when narrate quoted text is enabled. Defines the string of characters used to introduce separation between between the groups of extracted quoted text sent to the provider. The provider will use this to introduce pauses by default using ...

processText(text)

Optional. A function applied to the input text before passing it to the TTS generator. Can be async.