Streaming TTS and STT models built on delayed-streams modeling, from the French Kyutai lab
Kyutai TTS & STT is listed under AI Voice & Speech, in the Content & Media Generation category on Flocci AI Tools. Streaming TTS and STT models built on delayed-streams modeling, from the French Kyutai lab. It is free, with no paid plan attached, and it lives at github.com.
Kyutai TTS & STT is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 397 entries on Flocci AI Tools with no upgrade path built in.
Kyutai TTS & STT needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on self-hosting, the command line and Mac.
Kyutai TTS & STT does 3 things the catalog singles out: Streaming tts and stt models built on delayed-streams modeling, from the french kyutai lab; low-latency text-in streaming speech, english and french; apache-2.0; powers the unmute voice assistant demo.
Copilot Audio Expressions is the closest free alternative: it sits in the same AI Voice & Speech sub-category and is free. Kokoro Web, Zonos and Chatterbox (Resemble AI) also start free. The full list is on the alternatives page.
See the full list →