---
title: TADA — Text-Acoustic Dual Alignment for Speech
emoji: 🗯️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 6.9.0
python_version: 3.11.9
app_file: app.py
pinned: true
suggested_hardware: a10g-large
hf_oauth: true
hf_oauth_scopes:
  - gated-repos
short_description: Speech generation from text and acoustic reference
---