OpenSound PRO

OpenSound

15 4 31

AI & ML interests

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

Organizations

spaces 6

114

SoloSpeech

🎯

State-of-the-art target speech extractor

EzAudio ControlNet

🟣

Generate custom sound clips from text and a reference audio

273

EzAudio

🟣

Generate or edit realistic audio from text prompts

FlexSED

🎧

an open-vocabulary sound event detection model

100

CapSpeech TTS

🧢

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

SoloAudio

🎯

Separate sounds from audio mixtures using text prompts

models 5

datasets 20

OpenSound/CapSpeech-AgentDB-Audio

Updated Aug 5, 2025 • 14

OpenSound/CapSpeech-AgentDB

Viewer • Updated Jul 28, 2025 • 10.1k • 31

OpenSound/CapSpeech-SEDB-test

Viewer • Updated Jul 28, 2025 • 496 • 26

OpenSound/CapSpeech-SEDB

Viewer • Updated Jul 28, 2025 • 500 • 23

OpenSound/CapTTS-SFT

Viewer • Updated Jul 28, 2025 • 387k • 33 • 3

OpenSound/CapSpeech-PT

Viewer • Updated Jul 28, 2025 • 11.4M • 221 • 2

OpenSound/CapSpeech-PT-SEDB-HQ

Viewer • Updated Jun 4, 2025 • 198k • 26

OpenSound/CapSpeech-PT-SEDB-Audio

Viewer • Updated Jun 4, 2025 • 1.03M • 156

OpenSound/CapSpeech-SEDB-Audio

Viewer • Updated Jun 4, 2025 • 500 • 18

OpenSound/CapSpeech-CommonVoice

Viewer • Updated Jun 4, 2025 • 31.5k • 6 • 1

View 20 datasets