Skip to content

feat(google-tts): add prompt to normal synthesize for Gemini TTS #4208

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
davidzhao merged 1 commit into from
Dec 18, 2025
Merged

feat(google-tts): add prompt to normal synthesize for Gemini TTS #4208

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion livekit-plugins/livekit-plugins-google/livekit/plugins/google/tts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,7 @@ def __init__(
Args:
language (SpeechLanguages | str, optional): Language code (e.g., "en-US"). Default is "en-US".
gender (Gender | str, optional): Voice gender ("male", "female", "neutral"). Default is "neutral".
voice_name (str, optional): Specific voice name. Default is an empty string.
voice_name (str, optional): Specific voice name. Default is an empty string. See https://docs.cloud.google.com/text-to-speech/docs/gemini-tts#voice_options for supported voice in Gemini TTS models.
voice_cloning_key (str, optional): Voice clone key. Created via https://cloud.google.com/text-to-speech/docs/chirp3-instant-custom-voice
model_name (str, optional): Model name for TTS (e.g., "gemini-2.5-flash-tts"). Enables Gemini TTS models with streaming support.
prompt (str, optional): Style prompt for Gemini TTS models. Controls tone, style, and speaking characteristics. Only applied to first input chunk in streaming mode.
Expand Down Expand Up @@ -285,6 +285,9 @@ async def _run(self, output_emitter: tts.AudioEmitter) -> None:
text=self._input_text, custom_pronunciations=self._opts.custom_pronunciations
)

if self._opts.prompt is not None:
tts_input.prompt = self._opts.prompt

response: SynthesizeSpeechResponse = await self._tts._ensure_client().synthesize_speech(
input=tts_input,
voice=self._opts.voice,
Expand Down
Loading