OpenSound PRO

OpenSound

🎧 We build open-source models for audio, speech, and music.

updated a dataset about 9 hours ago

updated a dataset about 9 hours ago

OpenSound/CapSpeech-SEDB

updated a dataset about 9 hours ago

OpenSound/CapTTS-SFT

OpenSound 's Spaces 5

Stylized TTS – design voice, accent, and emotion your way

Generate audio from text and reference audio

State-of-the-art target speech extractor

Generate and edit audio from text prompts

Separate sounds from audio mixtures using text prompts