---
title: VoiceCraft
emoji: ✏️
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.24.0
python_version: "3.10.13"
app_file: app.py
pinned: false
license: cc-by-nc-sa-4.0
short_description: Edit English speech, keeping the surrounding take
tags:
  - category:generation
  - subcategory:editing
  - domain:speech
  - input:audio
  - input:text
  - output:audio
  - sample-rate:16000
  - channels:mono
  - speech-editing
startup_duration_timeout: 1h
preload_from_hub:
  - pyp1/VoiceCraft_830M_TTSEnhanced config.json,model.safetensors 15ff81999431f57897a945a0d261a561a02ea342
  - pyp1/VoiceCraft encodec_4cb2048_giga.th
---

# VoiceCraft

Replace a timed segment of English speech. Upload a recording, enter the full
target transcript, and set the edit start and end times. The result is a 16 kHz
WAV file.

HARP endpoints: `/controls`, `/process`, `/cancel`.

[Sources and licenses](SOURCES.md)