Hello, how do we fetch models and voices for each provider if we use inference for stt? And how do we fetch models and supported languages for each provider if we use inference for tts?

Hi, the documentation has been updated to list the available STT and TTS models in a separate section in the left-hand menu for 'LiveKit Inference'. See https://docs.livekit.io/agents/models/stt/inference/assemblyai/ and https://docs.livekit.io/agents/models/tts/inference/cartesia/. The starter agent has also been updated to show use: https://github.com/livekit-examples/agent-starter-python/blob/main/src/agent.py#L65

I see, so there is no api to fetch these

Correct

thank you so much!