EryriLabs/pocket-tts-GGUF

Pocket TTS — GGUF (all languages)

GGUF conversions of Kyutai's Pocket TTS, for use with llama.cpp. Pocket TTS has been ported to ONNX, CoreML and MLX, and other GGUF conversions exist — but they ship without the multimodal projector. To our knowledge these are the first complete model + mmproj pairs that run directly on llama.cpp's built-in Pocket TTS support (llama-tts).

Pocket TTS is a 100M-parameter (24-layer French: ~300M) text-to-speech model designed by Kyutai to run efficiently on CPUs. On a desktop CPU these GGUFs synthesize at **5.5–6x realtime** (French ~2.9x) — no GPU needed.

Languages

Pocket TTS ships one complete model per language. Each is converted to a llama.cpp GGUF pair: a model file and an mmproj file (the Mimi codec and speaker encoder). Pass both to llama-tts. The mmproj files are per-language — same size, different weights — so keep each pair together.

Language	Files	Model size	Tested voice
English	pocket-tts-en.gguf + mmproj-pocket-tts-en.gguf (repo root)	152 MB	unmute-prod-website/default_voice.wav
French	french/pocket-tts-french.gguf + french/mmproj-pocket-tts-french.gguf	584 MB	cml-tts/fr/10087_11650_000028-0002_enhanced.wav
German	german/pocket-tts-german.gguf + german/mmproj-pocket-tts-german.gguf	152 MB	unmute-prod-website/default_voice.wav
Italian	italian/pocket-tts-italian.gguf + italian/mmproj-pocket-tts-italian.gguf	152 MB	unmute-prod-website/default_voice.wav
Portuguese	portuguese/pocket-tts-portuguese.gguf + portuguese/mmproj-pocket-tts-portuguese.gguf	152 MB	unmute-prod-website/default_voice.wav
Spanish	spanish/pocket-tts-spanish.gguf + spanish/mmproj-pocket-tts-spanish.gguf	152 MB	unmute-prod-website/default_voice.wav

French is converted from upstream's french_24l checkpoint — the only French variant Kyutai publishes. It has 24 transformer layers instead of 16, hence the larger file and the lower real-time factor.

All six pairs were verified on CPU by synthesizing a native-language sentence and checking the output is valid, non-silent audio.

Usage

Requires official ggml-org/llama.cpp at or after commit 9f0d017 — Pocket TTS support is merged upstream, so a stock build of llama-tts works; no fork or patch needed. A speaker reference file is effectively mandatory — the model produces almost no audio without one.

llama-tts -m pocket-tts-en.gguf -mm mmproj-pocket-tts-en.gguf \
  -p "Hello, this is Pocket TTS running locally." \
  --tts-speaker-file default_voice.wav --output out.wav

Output is 24 kHz mono WAV at ~12.5 frames/sec.

Voices: reference clips only supply timbre; the language is fixed by the weights. An English reference clip drives every language correctly, so you do not need a native-language sample. Voices come from kyutai/tts-voices, which currently carries a dedicated non-English set for French only (cml-tts/fr).

Spanish note: avoid starting prompts with a leading ¡ — it can truncate generation after a fraction of a second. Begin with the word itself.

For a warm, OpenAI-compatible HTTP server (POST /v1/audio/speech) and a full local voice-assistant chain (Gemma 4 audio-in → Pocket TTS out, ~1.3s to first audio), see llama-tts-server and its Jetson edition jetson-voice-assistant.

Provenance

Converted with llama.cpp's convert_hf_to_gguf.py at master commit 9f0d017, from kyutai/pocket-tts languages/<name> (base checkpoints; French from french_24l), F16/F32 tensors as emitted by the converter (no quantization).

License and attribution

CC-BY-4.0, same as the upstream model. Original model by Kyutai (kyutai/pocket-tts, paper). This repo only repackages the weights in GGUF format.