- Home
- Text-to-Speech Software
- Kyutai TTS
On the recordRead 12 Oct 202618 facts
Kyutai TTS
Kyutai TTS · Paris, France · founded 2023
Plans and prices
Kyutai Pocket TTS
Free
Open-source model; 100M parameters; runs on CPU; voice cloning; seven listed languages
Read 12 Oct 2026 · github.com
Kyutai TTS 1.6B
Free
Open-source streaming model; designed for servers and low-latency applications
Read 12 Oct 2026 · kyutai.org
On the record
- API access
- Yeskyutai.org · read 20 Sep 2026
- Browser demo
- The maker says visitors can try Pocket TTS in a browser without installing anything.github.com · read 12 Oct 2026
- Export formats
- WAVkyutai.org · read 20 Sep 2026
- Integration
- Kyutai says TTS 1.6B is used in Unmute, its interactive real-time speech demo.kyutai.org · read 12 Oct 2026
- Interfaces
- Pocket TTS provides a Python API, command-line interface, and local HTTP server.github.com · read 12 Oct 2026
- Languages
- The Pocket TTS repository lists English, French, German, Portuguese, Italian, Spanish, and Dutch support.github.com · read 12 Oct 2026
- License
- The Pocket TTS GitHub repository identifies its license as MIT.github.com · read 12 Oct 2026
- Limit
- The Pocket TTS repository lists adding silence in the input text to create pauses as unsupported.github.com · read 12 Oct 2026
- Organization
- Kyutai describes itself as an open-science AI research lab based in Paris.kyutai.org · read 12 Oct 2026
- Performance
- The repository reports about 200 ms to the first audio chunk and roughly six times real-time generation on a MacBook Air M4 CPU.github.com · read 12 Oct 2026
- Pocket TTS
- Pocket TTS is a 100-million-parameter model designed to run in real time on a CPU.kyutai.org · read 12 Oct 2026
- Product
- Kyutai describes TTS as two open-source text-to-speech models: Pocket TTS and Kyutai TTS 1.6B.kyutai.org · read 12 Oct 2026
- Runtime requirements
- Pocket TTS supports Python 3.10 through 3.14 and requires PyTorch 2.5 or later; it does not require the GPU version of PyTorch.github.com · read 12 Oct 2026
- Streaming model
- Kyutai TTS 1.6B can begin generating audio before the full text input is available, a design the maker says suits low-latency voice assistants.kyutai.org · read 12 Oct 2026
- Voice cloning
- Pocket TTS can clone a voice from an audio sample when run locally.kyutai.org · read 12 Oct 2026
