ugc-manual
由 pauldelavallaz 提供
Coding Agents & IDEs简介
Generate lip-sync video from image + user's own audio recording. ✅ USE WHEN: - User provides their OWN audio file.
描述
该技能的功能
Generates a lip-sync video by combining a face image with a user-provided audio recording. The person in the image is animated to match the audio using ComfyDeploy's UGC-MANUAL workflow. Use this when you already have an audio file and want to preserve the exact voice and timing.
Preserves the exact voice, timing, and delivery of the user's own recording instead of replacing it with AI-generated speech.
何时使用
- Animating a profile photo to match a recorded voice message
- Turning a Telegram or WhatsApp voice note into a talking-head video
- Syncing a character image to externally generated TTS audio
- Creating a video avatar that speaks in your own voice
- Producing lip-synced content from pre-recorded audio clips
示例工作流
User asks: Create a lip-sync video from my profile photo and this MP3 voice recording
- 1
Accept the image file and audio file from the user
- 2
Convert audio to WAV PCM 16-bit mono 48kHz via ffmpeg if not already in that format
- 3
Submit the image and converted audio to ComfyDeploy's UGC-MANUAL deployment endpoint
- 4
Poll the API for job completion
- 5
Retrieve and return the output MP4 to the user
MP4 video where the face in the image lip-syncs to the provided audio
前置要求
- ffmpeg installed on the system
安装
clawhub install pauldelavallaz/ugc-manual运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。