search

livekit / agents

Build real-time multimodal AI applications 🤖🎙️📹
https://docs.livekit.io/agents
Apache License 2.0
4.08k stars 433 forks source link

local STT and TTS #962

Open MSR2201 opened 1 month ago

MSR2201 commented 1 month ago

is there any way i can use local models for stt and tts instead of the api ones

KhasVN commented 1 month ago

This from the documentation:

Building your own
The plugin framework is designed to be extensible, allowing anyone to build their own plugin. Your plugin can integrate with various providers or directly load models for local inference.

By adopting the standard STT or TTS interfaces, you can abstract away implementation specifics and simplify switching between different providers in your agent code.

You can see the STT and TTS files for references to build your own

MSR2201 commented 1 month ago

can you give me an example code if you can? for whisper local model

billyg88 commented 21 hours ago

Any examples for local whisper SpeechToText would be greatly appreciated !