feat(rumik-ai): add Rumik AI TTS plugin#6234
Open
YashrajKupekar17 wants to merge 1 commit into
Open
Conversation
Add livekit-plugins-rumik-ai, a streaming TTS plugin backed by Rumik's Silk WebSocket API (muga/mulberry voice models). Includes the plugin package, unit tests, two examples, manifest/lockfile registration, and .env.example entries.
|
|
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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-rumik-ai, a streaming text-to-speech plugin forRumik AI's Silk voices. It exposes both Silk models through
one
rumik_ai.TTSinterface:silk muga 1) - expressive Romanized Hinglish emotion TTS. Each linestarts with one global tone tag -
[happy],[excited],[sad],[angry],[neutral],[whisper]- with optional inline events<laugh>,<chuckle>,<sigh>. Tuned for short, natural spoken lines (reactions, banter, support).silk mulberry 1.5) - faster, description-driven voice for**English and code-mixed sentences. Steer it with a natural-language
description, or a presetspeaker(speaker_1–speaker_4). Streams, so it suits low-latency agents.Config: RUMIK_API_KEY (required), RUMIK_GATEWAY_URL (optional gateway override).
Model and prompting reference: https://docs.rumik.ai