FreeVideo
App window with zoom
- 365365 downloads
- 125125 likes
- 188188 saves
Works with
+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
Character voice and lip-sync pipeline v1.0.0
Use this resource to create a character's voice and sync it to video
New
- 495 downloads
- 178 likes
- 153 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install character-voice-lipsync-pipelineWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent picks a speech tool based on your audio samples (Chatterbox, F5-TTS, RVC, ElevenLabs), prepares the text and audio, then runs lip-sync (Wav2Lip, SadTalker, LivePortrait). Three pipelines, quick, quality and premium, detail each step. You get a talking character video with a consistent voice.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- ComfyUI (Chatterbox, F5-TTS, Wav2Lip)
- Uses
- ComfyUI
- FFmpeg
- Licence
- MIT
Similar resources
View all- Free
FreeVideo
One big number
- 463463 downloads
- 223223 likes
- 100100 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
PalateKit Motion, the library
- 338338 downloads
- 198198 likes
- 249249 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Three bars head to head
- 348348 downloads
- 133133 likes
- 182182 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Before / after slider
- 322322 downloads
- 248248 likes
- 238238 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Three-card carousel
- 418418 downloads
- 157157 likes
- 101101 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Chat exchange
- 564564 downloads
- 127127 likes
- 161161 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
PROVideo
Checklist ticking off
- 442442 downloads
- 233233 likes
- 160160 saves
Works with+ HyperFrames- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: decision tree and tool reference
- Typical settings for Chatterbox, Wav2Lip, SadTalker and LivePortrait
- Three talking-head pipelines, from fastest to most polished
- A troubleshooting table and FFmpeg audio preparation commands
Good fit for
- Giving a voice to a mascot or brand avatar
- Dubbing a video with a voice cloned from a sample
- Producing virtual presenter videos for social media
Not for
- Composing music or sound effects
- Use without ComfyUI or a machine able to run these models
- Cloning someone's voice without their consent
Tags
- voice
- tts
- voice cloning
- lip-sync
- comfyui
About
You say
"Create my character's voice from this 10-second sample, then sync it to this animated image."
Skill published by mckruz under the MIT license.
Show moreShow less
Prerequisites
- You bring
- The lines the character should say and A voice sample and a character image
- Dependencies
- ComfyUI and FFmpeg
- External costs
- ElevenLabs subscription needed only if you choose that tool Billed by the provider, on your account.
How to use it
- Install the skill and check that your ComfyUI server responds.
- Provide the character's lines and, if possible, a voice sample.
- Choose one of the three pipelines and review the result.
Content preview
Files
- LICENSE1.1 KB
- NOTICE-PALATEKIT.md0.4 KB
- SKILL.md7.6 KB
Origin and licence
Modified by PalateKit
- Author
- mckruz
- Source
- github.com/mckruz/comfyui-expert/tree/dee27dc3d69b609c0006a8a12e71aadfc475ae95/skills/comfyui-voice-pipeline
- Licence
- MIT
Notice
Version modifiée de « comfyui-voice-pipeline » (mckruz, MIT) : traduction française et fiche par PalateKit.
User reviews
–
No ratings yet
Loading reviews…
Frequently asked questions
Are the referenced files included?
No. The file points to neighboring documents (references/voice-synthesis.md, models.md) that are not shipped; the main guide works without them, but you will need to find the models yourself.
Do I need a paid account?
Only if you choose ElevenLabs. The other tools are open source but need suitable hardware.