Views
No views yet
| Model | Description | Size |
|---|---|---|
| cond_step | KV cache prefill (voice + text conditioning) | ~200MB |
| flowlm_step | Autoregressive generation (transformer_out + EOS) | ~200MB |
| flow_decoder | Flow matching denoiser (8 Euler steps per frame) | ~190MB |
| mimi_decoder | Streaming audio codec (1920 samples per frame) | ~11MB |
constants_bin/:alba (default), azelma, cosette, javert1import FluidAudioTTS
2
3let manager = PocketTtsManager()
4try await manager.initialize()
5let audio = try await manager.synthesize(text: "Hello, world!")
6
7See https://github.com/FluidInference/FluidAudio for the full Swift framework.
8
9License
10
11CC-BY-4.0, inherited from https://huggingface.co/kyutai/pocket-tts. Attribution to Kyutai is required.
12
13References
14
15- https://huggingface.co/kyutai/pocket-tts
16- https://arxiv.org/abs/2410.00037
17- https://github.com/FluidInference/FluidAudio