AI Models
Explore the open AI voice and speech models we host and document — try them live in your browser, then dive into a dedicated guide for each one. New models are added here as they launch.
Available AI models
Each model has its own page with a live demo, capabilities and an honest, hands-on guide.
OmniVoice
k2-fsa's open-source diffusion-LM TTS for 600+ languages, with zero-shot voice cloning and attribute-based voice design. Try the official Hugging Face demo embedded on Whisper Web.
VoxCPM
OpenBMB's tokenizer-free VoxCPM2 TTS model for 30 languages, voice design, controllable voice cloning and 48 kHz speech. Try the official Hugging Face demo embedded on Whisper Web.
More models coming soon
We're adding more open AI voice and speech models to this directory. Check back soon, or start with VoxCPM today.
Looking for transcription?
These models pair well with our core browser-based speech-to-text workspace.