F5-TTS Audio Generation

Generate high-quality audio with a fine-tuned F5-TTS model. Upload reference audio, use Whisper ASR for transcription, enter text, adjust speed, and select or upload model files.

Reference Audio

Use Whisper ASR for Transcription

Reference Text

Generated Text

Generated Audio

Status

Speed

0.5 2

Model Config (*.yaml)

Checkpoint File (*.pt or *.safetensors)

Vocab File (*.txt or *.safetensors)

Upload Custom Model Files

Example Inputs

Reference Audio	Reference Text	Generated Text