{"library":"omnivoice","title":"OmniVoice","description":"OmniVoice is a zero-shot text-to-speech library using diffusion language models. It supports multilingual TTS with voice cloning from short audio samples. Current version 0.1.5, actively maintained. Requires Python >= 3.10.","language":"python","status":"active","last_verified":"Sat May 09","install":{"commands":["pip install omnivoice"],"cli":null},"imports":["from omnivoice import OmniVoice","from omnivoice import infer"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"from omnivoice import OmniVoice, infer\n\n# Load model\nmodel = OmniVoice.from_pretrained(\"k2-fsa/OmniVoice\")\n\n# Synthesize speech\naudio = infer(model, text=\"Hello world\", reference_audio=\"ref.wav\", reference_text=\"The quick brown fox\")\n\n# Save to file\nimport torchaudio\ntorchaudio.save(\"output.wav\", audio.unsqueeze(0), 24000)","lang":"python","description":"Basic TTS inference with voice cloning.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}