If I look at ElevenLabs TTS | LiveKit Documentation I can see the list of elevenlabs TTS models, I do not see Eleven v3, as it is a really rich TTS model with multiple languages support: Models | ElevenLabs Documentation
Is there any reason to not support it through Livekit inference?
First I though it can only be used with dialouge API, but in the doc it states:
With Eleven v3 comes a new Text to Dialogue API, which allows you to generate natural, lifelike dialogue with high emotional range and contextual understanding across multiple languages. Eleven v3 can also be used with the Text to Speech API to generate natural, lifelike speech with high emotional range and contextual understanding across multiple languages.
When I tried with:
tts=inference.TTS(
model="elevenlabs/eleven_v3", voice="Xb7hH8MSUJpSbSDYk0k2", language="bn"
),
I get this error:
provider instance for session 4b1dc706-00d3-49ce-a197-749c9be56be0: TTS model not found in list"}, retrying in 2.0s
It would be really helpful if the Livekit team can help me here. Thanks in Advance!