README.md

---
title: Higgs Audio v3 TTS
emoji: 🔊
colorFrom: yellow
colorTo: green
sdk: gradio
sdk_version: "6.16.0"
python_version: "3.12"
app_file: app.py
startup_duration_timeout: 1h
pinned: false
short_description: Higgs Audio v3 voice cloning with a large voice gallery
---

# Higgs Audio v3 TTS

Zero-shot text-to-speech and voice cloning with
[`higgs-audio-v3-tts-4b`](https://huggingface.co/bosonai/higgs-audio-v3-tts-4b),
using the transformers port at
[`multimodalart/higgs-audio-v3-tts-4b-transformers`](https://huggingface.co/multimodalart/higgs-audio-v3-tts-4b-transformers).

Browse the voice gallery, preview a voice, select it, and enter the text to
synthesize. The selected reference clip is transcribed on CPU with Whisper to
improve voice cloning.

Generation requests use the ZeroGPU `large` allocation.