Add Qwen 3 TTS support for Simplismart-livekit plugin#5474
Merged
tinalenguyen merged 1 commit intolivekit:mainfrom Apr 21, 2026
Merged
Add Qwen 3 TTS support for Simplismart-livekit plugin#5474tinalenguyen merged 1 commit intolivekit:mainfrom
tinalenguyen merged 1 commit intolivekit:mainfrom
Conversation
![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.
simplipratik
force-pushed
the
integration/qwen3-tts
branch
2 times, most recently
from
e2ff8c2 to
0228713
Compare
simplipratik
changed the title
u9g
reviewed
Apr 17, 2026
| if options is None: | ||
| self._opts = SimplismartTTSOptions() | ||
| is_qwen = False | ||
| elif isinstance(options, QwenTTSOptions): |
Contributor
There was a problem hiding this comment.
Setting model="qwen-tts" or base_url=QWEN_BASE_URL without options=QwenTTSOptions(...) sends Orpheus-format JSON to the Qwen endpoint. Is there a better way we can approach the is_qwen check?
simplipratik
force-pushed
the
integration/qwen3-tts
branch
from
0228713 to
8c1a0ba
Compare
| # sample_rate controls how the framework decodes/plays back the returned PCM audio; | ||
| # it is not sent to the server. | ||
| sample_rate: int = 24000, | ||
| options: SimplismartTTSOptions | QwenTTSOptions | None = None, |
Member
There was a problem hiding this comment.
i would unpack the params in these options and avoid exposing the options object here, ideally the user wouldn't have to import anything to pass any parameters. i think we can also keep the defaults here for clarity
i recommend following the pattern rime has here: https://github.com/livekit/agents/blob/main/livekit-plugins/livekit-plugins-rime/livekit/plugins/rime/tts.py
simplipratik
force-pushed
the
integration/qwen3-tts
branch
from
8c1a0ba to
e57bdd2
Compare
| if self._opts.qwen_options is not None: | ||
| qwen_opts = self._opts.qwen_options | ||
| payload: dict = { | ||
| "text": self._input_text, |
Member
There was a problem hiding this comment.
Suggested change
| "text": self._input_text, | |
| "model": self._opts.model, | |
| "text": self._input_text, |
i got this error when trying qwen:
livekit.agents._exceptions.APIStatusError: message='Simplismart TTS API Error: {"error":"Missing required field: model"}', status_code=400,
retryable=False, body={"error":"Missing required field: model"}
| "Accept": "audio/L16", | ||
| } | ||
| else: | ||
| assert self._opts.simplismart_options is not None |
Member
There was a problem hiding this comment.
we can remove this line, simplismart_options will always be set in this else from the init
Suggested change
| assert self._opts.simplismart_options is not None |
simplipratik
force-pushed
the
integration/qwen3-tts
branch
from
f281b86 to
e97c4ae
Compare
| "model": self._opts.model, | ||
| "text": self._input_text, | ||
| "language": qwen_opts.language, | ||
| "speaker": self._opts.voice, |
Member
There was a problem hiding this comment.
Suggested change
| "speaker": self._opts.voice, | |
| "voice": self._opts.voice, |
- Add `qwen-tts` to `TTSModels` - Add `_SimplismartTTSOptions` and `_QwenTTSOptions` private dataclasses following the rime plugin pattern (flat params, no public Options objects) - Auto-detect `base_url`, `model`, and `voice` from model name via `_is_qwen_model()` - Defaults set for Orpheus model; Qwen 3 defaults auto-applied when model name contains `qwen` - All verbose logging changed to `logger.debug` - `sample_rate` documented as framework-only, not sent to server - Backwards compatible: existing `TTS()` usage unchanged - Add `model` field to Qwen payload (fixes `Missing required field: model` error) Made-with: Cursor
simplipratik
force-pushed
the
integration/qwen3-tts
branch
from
e97c4ae to
09030ab
Compare
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
3 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.
Summary
This PR adds Qwen 3 TTS support to the SimpliSmart LiveKit plugin while maintaining full backwards compatibility with the existing Orpheus TTS implementation.
Changes
qwen-ttstoTTSModelsinmodels.pyQwenTTSOptionsclass for Qwen 3 specific configuration (language,leading_silence)TTSclass to accept anoptionsparameter that can be eitherSimplismartTTSOptionsorQwenTTSOptionsChunkedStream._run()to use type-based payload construction for the appropriate API formatstt.pypatterns)QwenTTSOptionsandSimplismartTTSOptionsfrom the moduleUsage
Legacy Orpheus (backwards compatible)
Qwen 3 TTS
Files Changed
livekit-plugins/livekit-plugins-simplismart/livekit/plugins/simplismart/__init__.pylivekit-plugins/livekit-plugins-simplismart/livekit/plugins/simplismart/models.pylivekit-plugins/livekit-plugins-simplismart/livekit/plugins/simplismart/tts.py