Text-to-Speech
Pocket-TTS
Safetensors
MLX
English
apple-silicon
speech
speech-generation
tts
mlx-audio
on-device
offline
openvox
Instructions to use theoracleguy/pocket-tts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use theoracleguy/pocket-tts with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("theoracleguy/pocket-tts") 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()) - MLX
How to use theoracleguy/pocket-tts with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir pocket-tts theoracleguy/pocket-tts
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Xet hash:
- 9057cee178070fe05d7f93472c0a9221667018f24b196da0f2388992c88a01c2
- Size of remote file:
- 6.54 MB
- SHA256:
- 223f60a58a28236b27ca361e01f182fb919e72f0e3dceffb3bf18f006a0d0097
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.