StyleTTS 2
TTS
Human-level TTS with style transfer. Community ONNX export available but multi-stage pipeline (encoder, diffusion, vocoder) needs custom integration.
WebGPU
WASM
MIT
Not Yet Supported
StyleTTS 2 is not yet supported in TTSLab. Upvote to help us prioritize and get notified when support is added.
Get notified when this model is supported:
Try Similar Models
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.
Supertonic 2
Lightning-fast multilingual TTS by Supertone. 10 voices, 5 languages, 167x faster than real-time. ONNX-native with WebGPU support.