Instructions to use optimotion/suzi-voice-packs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Pocket-TTS
How to use optimotion/suzi-voice-packs with Pocket-TTS:
from pocket_tts import TTSModel import scipy.io.wavfile tts_model = TTSModel.load_model("optimotion/suzi-voice-packs") 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
Suzi voice packs
On-demand speech packs downloaded by the Suzi desktop app. No account is needed to download.
pocket-tts-tr-v1.tar.gz (Turkish)
- Source model: wite-tech/pocket-tts-turkish (CC BY 4.0), a Turkish model based on Pocket TTS by Kyutai.
- Runtime graphs: KevinAHM/pocket-tts-onnx (CC BY 4.0).
- Changes: weight format conversion to ONNX only (int8 quantised main and flow graphs; fp32 mimi decoder).
- SHA-256:
ace851da355e01a6832244c2fe2ec182eb23517463b37f3551284f53fca513a3
Licensed under CC BY 4.0. See ATTRIBUTION.txt inside the archive.
- Downloads last month
- -