RepoRadar
Leave a Tip
Item detail

OpenBMB/VoxCPM (VoxCPM2 TTS)

VoxCPM2 is an Apache-2.0 multilingual text-to-speech and voice-design project from OpenBMB with tokenizer-free TTS, creative voice design, and voice-cloning workflows. It is not new this hour, but it is gaining GitHub momentum and is a practical open audio model stack for builders who need local or controllable speech generation.

Open source →Back to radar
Score7.7
Popularity84.0
Riskmedium
TierGold
Score breakdown
Usefulness8.0
Novelty7.0
Momentum9.0
Maturity7.5
Open-source/build8.4
Evidence7.2
Workflow potential8.1
Setup ease4.2

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for audio AI builders and product teams prototyping multilingual TTS: test quality and latency on consenting voices only, and review the compute requirements before promising real-time use.

Who should use it

audio AI developerslocal model usersmultilingual app teamsresearchers working on speech generation

Who should skip it

Skip or sandbox it if you cannot review permissions, data access, and failure modes before use.

Risk explanation

voice cloning requires consent and abuse safeguards; larger speech models can require significant compute.

Evidence links

Closest alternatives / related signals

ttsvoice-cloningmultilingualopenbmbaudio-ai