Instructions to use kyutai/pocket-tts-without-voice-cloning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use kyutai/pocket-tts-without-voice-cloning with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("kyutai/pocket-tts-without-voice-cloning") 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
Ctrl+K
- 6.19 MB xet
- 7.82 MB xet
- 7.96 MB xet
- 6.74 MB xet
- 5.26 MB xet
- 6.19 MB xet
- 6.19 MB xet
- 6.93 MB xet
- 8.26 MB xet
- 6.54 MB xet
- 6.54 MB xet
- 6.24 MB xet
- 4.62 MB xet
- 7.37 MB xet
- 6.19 MB xet
- 6.19 MB xet
- 6.24 MB xet
- 5.95 MB xet
- 6.19 MB xet
- 6.19 MB xet
- 7.28 MB xet
- 6.98 MB xet
- 3.74 MB xet
- 6.19 MB xet
- 5.26 MB xet
- 6.74 MB xet