heygen-lipsync

n8n community node for HeyGen's Lipsync (Precision/Speed) and Text-to-Speech (Starfish) APIs — text-to-speech with voice/tone/language control, piped into video lipsync.

Package Information

Released: 2 mo ago
Downloads: 0 weekly / 0 monthly
Latest Version: 1.0.0

Available Nodes

Documentation generating…

HeyGen Lipsync AI icon
HeyGen Lipsync AI
Generate speech (with tone/language control) and lipsync it onto video using the HeyGen API

Documentation

n8n-nodes-heygen-lipsync

An n8n community node for HeyGen, covering text-to-speech and lipsync generation.

Installation

Follow the n8n community nodes installation guide, or install manually:

npm install n8n-nodes-heygen-lipsync

Credentials

Requires a HeyGen API credential:

Field Description
API Key Your HeyGen API key
Base URL Defaults to https://api.heygen.com

Operations

The HeyGen Lipsync AI node supports:

  • Text → Speech → Lipsync (Full Pipeline, Wait) — generates speech from text (with voice/tone/language control), lipsyncs it onto a video, polls until done, and returns the final video URL. Handles the whole chain in one step.
  • Generate Speech Only (Text to Speech) — turns text into an audio file.
  • Create Lipsync (From Existing Audio) — syncs an existing audio track onto a video and returns immediately with a job ID.
  • Get Lipsync Status / List Lipsyncs / Update Lipsync Title / Delete Lipsync — manage lipsync jobs.
  • List Voices — search available voices by language (including Amharic), gender, and engine.
  • Upload Asset (Binary → Asset ID) — uploads binary video/audio/image from the workflow and returns an asset_id for use in other operations.

Video and image inputs across operations can be provided as a public URL, a previously uploaded Asset ID, or raw binary data from an earlier node (uploaded automatically first).

Tone options for speech generation include Neutral, Happy/Upbeat, Excited, Calm, Sad, Serious, Soft/Gentle, and full custom SSML.

License

MIT

Discussion