feat: add SILMA AI TTS plugin - #7160
Open
karimouda wants to merge 3 commits into
Open
Conversation
Adds livekit-plugins-silma, a text-to-speech plugin for SILMA AI's TTS v2 models: English, Modern Standard Arabic, and the Saudi (Najdi) dialect. - stream() uses the full-duplex WebSocket endpoint with pooled connections and sentence tokenization, so each request is a complete utterance. - synthesize() uses the binary waveform endpoint (POST /stream). - SILMA returns a 24 kHz mono float32 waveform; the plugin converts it to 16-bit PCM, buffering samples that straddle a chunk boundary. - The API caps text at 250 characters per request, so longer input is split on word boundaries. SILMA's <STAG_PN>/<STAG_EMAIL>/<STAG_LINK> pronunciation hints are kept intact across that split. - Supports cloned voices (custom_audio_id) and account-level pronunciation overrides. Includes offline unit tests covering configuration, float32 decoding, text splitting, the HTTP and WebSocket paths, and connection-reuse behavior. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDYW9y4sTu68aV2ZuPQuAB
|
|
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
… is now not allowed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds livekit-plugins-silma, a text-to-speech plugin for SILMA AI's TTS v2 models: English, Modern Standard Arabic, and the Saudi (Najdi) dialect.
Tested against the live API. Includes 44 offline unit tests covering configuration, float32 decoding, text splitting, both transports, and connection-reuse behavior.
I maintain SILMA and I’m happy to keep this plugin up to date. If needed, I can also provide a test API key. I’m glad to draft the documentation page content as well, if that would be helpful.