Lokutor Is Now a LiveKit Agents Plugin

Lokutor's speech recognition and text-to-speech are now available as a LiveKit Agents plugin, with livekit-plugins-lokutor merged into the livekit/agents repository on 12 November 2026. The lokutor.STT and lokutor.TTS plugins each handle nine languages — English, Spanish, Catalan, Galician, Basque, Portuguese, French, Italian and German — with a single model per direction, so existing LiveKit agents can switch speech providers by changing only the stt= and tts= lines. The package is expected on PyPI with LiveKit's next release, and can be installed from LiveKit's repository in the meantime.

Lokutor is now a plugin for LiveKit Agents https://docs.livekit.io/agents/ . livekit-plugins-lokutor was merged into livekit/agents https://github.com/livekit/agents/pull/7256 on 12 November 2026, and it gives any LiveKit agent our speech recognition and our voices. LiveKit https://livekit.io is open-source infrastructure for realtime audio and video. LiveKit Agents is its Python framework for voice agents that join a room or a phone call. The framework runs the conversation: the room, turn-taking, interruptions and the language model. Plugins supply the speech in and out. lokutor.STT lokutor.TTS Both work in English, Spanish, Catalan, Galician, Basque, Portuguese, French, Italian and German. Each direction is one model for all nine languages, so there is no per-language routing to set up. python from livekit.agents import Agent, AgentServer, AgentSession, JobContext, cli from livekit.plugins import lokutor, openai, silero server = AgentServer @server.rtc session async def entrypoint ctx: JobContext - None: session = AgentSession stt=lokutor.STT language="es" , llm=openai.LLM , tts=lokutor.TTS voice="F1", language="es" , vad=silero.VAD.load , await session.start agent=Agent instructions="Eres una recepcionista amable." , room=ctx.room if name == " main ": cli.run app server If you already run a LiveKit agent, switching to Lokutor's speech means changing the stt= and tts= lines; the rest of the agent stays as it is. Install it with LiveKit Agents: pip install "livekit-agents lokutor ~=1.8" The package is expected to be published to PyPI with LiveKit's next release. Until then, the integration guide https://docs.lokutor.com/guides/livekit-integration shows how to install it from LiveKit's repository. If you want Lokutor to run the whole conversation, including the LLM, turn-taking, tools, phone numbers and recordings, use a Lokutor agent https://docs.lokutor.com/guides/my-first-agent instead. The plugin is for teams who already build on LiveKit and want our speech inside their pipeline. LOKUTOR API KEY . Thanks to the LiveKit team, who reviewed the plugin closely over several rounds. If you build something with it, tell us at contact@lokutor.com mailto:contact@lokutor.com . Try the voices in your browser on Hugging Face https://huggingface.co/spaces/lokutor-ai/tts-on-cpu . Lokutor is live on Product Hunt https://www.producthunt.com/products/lokutor?launch=lokutor .