# Kyutai TTS Review

> Kyutai TTS review: Research-lab open TTS optimized for real-time streaming (Delayed Streams Modeling); Pocket TTS targets on-device/CPU deployment while the.

![Kyutai TTS logo](https://www.versusref.com/logos/kyutai-tts.png)

Research-lab open TTS optimized for real-time streaming (Delayed Streams Modeling); Pocket TTS targets on-device/CPU deployment while the larger DSM TTS targets production streaming servers (Rust backend).

Among the 46 text-to-speech tools we track, Kyutai TTS has the 38th-widest language coverage.

See pricing · Open source · facts verified Jul 20, 2026

## What we know about Kyutai TTS

This is our verified profile of Kyutai TTS, a text-to-speech apis platform - research-lab open TTS optimized for real-time streaming (Delayed Streams Modeling); Pocket TTS targets on-device/CPU deployment while the larger DSM TTS targets production streaming servers (Rust backend). Every fact about Kyutai TTS below carries the source it came from and the day we checked it.

Kyutai TTS does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Kyutai TTS quote, it is the fastest way for us to close that gap.

On capabilities, Kyutai TTS covers streaming audio output, instant voice cloning, and self-host / on-prem option. Each of those is verified against Kyutai TTS's own docs or dashboard, not marketing copy.

Placed against the 46 text-to-speech tools we track, Kyutai TTS's strongest showing is the 38th-widest language coverage - a spread worth weighing against your own priorities.

In total we track 10 verified facts for Kyutai TTS today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Kyutai TTS fact sheet below.

## Fact sheet

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Streaming audio output | ✓  Yes | Jul 20 | [source](https://github.com/kyutai-labs/delayed-streams-modeling) |
| Instant voice cloning | ✓  Yes | Jul 20 | [source](https://huggingface.co/kyutai/tts-1.6b-en_fr) |
| Languages supported | 2 languages | Jul 20 | [source](https://huggingface.co/kyutai/tts-1.6b-en_fr) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://github.com/kyutai-labs/delayed-streams-modeling) |
| Model weights license | CC-BY-4.0 (weights) | Jul 20 | [source](https://huggingface.co/kyutai/tts-1.6b-en_fr) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | Python (PyTorch), Rust server, MLX (Swift/Apple) | Jul 20 | [source](https://github.com/kyutai-labs/delayed-streams-modeling) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | Pocket TTS: 100M | Jul 20 | [source](https://huggingface.co/kyutai/tts-1.6b-en_fr) |
| Hardware to self-host | Pocket TTS: CPU-only | Jul 20 | [source](https://github.com/kyutai-labs/pocket-tts) |
| Project maintenance status | active | Jul 20 | [source](https://github.com/kyutai-labs/delayed-streams-modeling) |
| GitHub stars | 2,980 stars | Jul 20 | [source](https://github.com/kyutai-labs/delayed-streams-modeling) |

Source: https://www.versusref.com/tts/tools/kyutai-tts/