Instructions to use TheStageAI/pocket-tts-18m-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use TheStageAI/pocket-tts-18m-en with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("TheStageAI/pocket-tts-18m-en") voice_state = tts_model.get_state_for_audio_prompt( "hf://kyutai/tts-voices/alba-mackenna/casual.wav" ) audio = tts_model.generate_audio(voice_state, "Hello world, this is a test.") # Audio is a 1D torch tensor containing PCM data. scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy()) - Notebooks
- Google Colab
- Kaggle
pocket-tts-18m-en โ TheStage Apple SDK engines
Core ML / ANE engines of the 18M-parameter English model of
kyutai/pocket-tts (english_18m_2026-10, CC-BY-4.0, Kyutai)
for the TheStage Apple SDK (model_type: pocket-tts).
subscription/macos_ios/engines.zip โ flow LM fp16 (8 layers, drifting flow head, ANE),
Mimi decoder fp32 (CPU), voices: azelma (default), alba, charles, cosette, javert, marius
(the released Pocket TTS voice states). QLPA-encrypted engines.
- Downloads last month
- -