react-native-executorch-pocket-tts

An ExecuTorch (.pte) export of kyutai-labs/pocket-tts for react-native-executorch (RNE). Independent export, not affiliated with Kyutai or Software Mansion.

pocket-tts is licensed MIT by Kyutai; this repo redistributes derived model weights under the same terms. Voice files are pocket-tts's own predefined voices (kyutai/tts-voices) — check that repo for per-voice licensing before redistributing further.

Status: XNNPACK-delegated, verified on-device

These .pte files are XNNPACK-delegated and verified end-to-end on an iPhone 17 simulator through RNE's generic ExecutorchModule binding (react-native-executorch 0.9.2, completely stock — no patches, no custom native modules): all three voices generate real speech, with the model signaling its own EOS, ~0.33x realtime on the simulator. Full pipeline, export scripts and the debugging writeup live in the pocket-tts-export project this was built from (notes/plan.md, notes/phase0-2-findings.md).

Export-side fixes that make the XNNPACK artifacts on-device-safe (see the export project's notes for the whole story — the original failure was a broken .pte serialization plus on-device-only XNNPACK kernel crashes, both fixed in the export):

• Mimi decode is two graphs (mimi_latent_step + mimi_pcm_step), split at the sub-frame/PCM boundary — a single merged graph at this context does not survive a fresh-process load.
• Every .pte is smoke-tested in a fresh process before shipping.
• Small streaming-tail op families (and the SEANet conv stack in mimi_pcm_step) are kept off the XNNPACK delegate, where RNE's bundled XNNPACK build crashes; the bulk linear/matmul work stays delegated.

Layout

Files live at the repo root on the v1 tag (the resolve/v1/<file> convention react-native-executorch uses):

text_conditioner.pte        16MB  - text tokens -> embeddings (dynamic seq len)
flow_lm_prompt_step.pte    264MB  - text embeddings -> primed KV cache (dynamic prompt len)
flow_lm_decode_step.pte    341MB  - one autoregressive decode step (6-layer transformer)
mimi_latent_step.pte        24MB  - latent frame -> 16 decoder sub-frames + state
mimi_pcm_step.pte           16MB  - sub-frames + conv state -> 1920 PCM samples
state_manifest.json               - exact state tensor shapes + emb_mean/emb_std, for the JS driver
tokenizer.json                    - SentencePiece tokenizer (HF format)
voices/
  alba.safetensors          12MB
  george.safetensors        12MB
  eve.safetensors           12MB

Consuming these

.pte files here are not loadable through RNE's TextToSpeechModule — that's hardcoded to Kokoro's graph shape. Load each file through RNE's generic ExecutorchModule binding instead and drive the prompt → decode → Mimi loop yourself: text_conditioner → flow_lm_prompt_step (on the voice-primed caches) → [flow_lm_decode_step + mimi_latent_step + mimi_pcm_step] per autoregressive step. pocket-tts-export's mobile-demo/App.tsx is a complete reference implementation.