🗣️ Audio8 TTS Preview 0.1B

Zero-shot voice cloning with a ~170M parameter TTS model (plus a 120M codec) — the smallest zero-shot TTS worth running. Give it text, a short reference clip and that clip's transcript.

Model · GitHub · Audio samples

Text to speak

Reference voice (optional)

Reference transcript

Exactly what is said in the reference clip.

Generated speech

Reference voices below come from the authors' Apache-2.0 Space Edge0/Audio8-TTS-Preview-0.6b. Only clone a voice you have permission to use, and disclose synthetic audio.

Examples