OpenSound's picture

OpenSound PRO

OpenSound

·

AI & ML interests

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

Recent Activity

new activity 1 day ago

OpenSound/CapSpeech-models:Add pipeline tag and library name

new activity 1 day ago

OpenSound/EzAudio:Add pipeline_tag and paper link

updated a Space 3 days ago

OpenSound/CapSpeech-TTS

View all activity

Organizations

upvoted a paper 22 days ago

CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech

Paper • 2506.02863 • Published 25 days ago • 8

upvoted 2 papers about 1 month ago

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline

Paper • 2505.19314 • Published May 25 • 4

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits

Paper • 2505.14648 • Published May 20 • 8