Kyutai Pocket TTS vs Kokoro-82M
Two open-source models that run fully in your browser — compared on the numbers that matter, with both available to try free so you can hear the difference on your own text.
| Kyutai Pocket TTS | Kokoro-82M | |
|---|---|---|
| Parameters | 100M | 82M |
| Download | 189 MB | 88 MB CPU / 310 MB WebGPU |
| Quality rank (of our lineup) | #3 | #2 |
| Speed | First audio in ~1s, streams ahead of playback on a modern CPU. | ≈ real-time on a modern CPU (WASM); 2–6× faster than real-time with WebGPU. |
| Voices | 28 | 28 |
| Languages | 1 | 2 |
| Voice cloning | Yes | No |
| Streaming | Yes | Yes |
| Hardware | Any CPU (WASM) | CPU ok, WebGPU faster |
| License | CC-BY-4.0 (weights), MIT (code) | Apache-2.0 |
| Output | 24.0 kHz | 24.0 kHz |
Which should you choose?
- Kokoro-82M if you want the most natural output and your device meets its requirements (≈ real-time on a modern CPU (WASM); 2–6× faster than real-time with WebGPU.).
- Kyutai Pocket TTS if download size or low-end hardware matters — it needs 189 MB and runs on any CPU.
- Kyutai Pocket TTS if you want to clone a voice from reference audio.
Frequently asked questions
Which sounds better, Kyutai Pocket TTS or Kokoro-82M?
Kokoro-82M ranks higher for naturalness in our lineup. But "better" depends on the job — Kyutai Pocket TTS wins when download size or low-end hardware matters — it needs 189 MB and runs on any CPU. Generate the same sentence with each and let your ears decide.
Are these comparisons measured or copied?
Speed and size figures come from the models' published specs and our own in-browser runs; the benchmark page lets you reproduce every number on your own hardware.