F5-TTS
TTS
Zero-shot voice cloning via flow matching. 3-component ONNX pipeline. Browser demo proven by third party. Needs custom ONNX Runtime integration.
WebGPU
WASM
CC-BY-NC-4.0
Coming Soon
F5-TTS is planned for a future release. Upvote to show your interest and get notified when it's ready.
Get notified when this model is supported:
Try Similar Models
Kokoro 82M
High-quality TTS with 21 voices. Best quality-to-size ratio for browser inference. Supports streaming generation.
Piper EN-US Lessac Medium
Fast, lightweight TTS using the VITS architecture. Part of the Piper project with 904+ voices across languages.
SpeechT5
Microsoft's unified-modal SpeechT5 model. Lightweight and CPU-sufficient for basic TTS needs.