MCP / Models / Reference video, editing and lip sync
MiniMax H3 Max Lip Sync MCP: a face that speaks your audio
MiniMax H3 Max Lip Sync makes a picture of a face speak your audio: a video as long as the audio, from 480P to 2K. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use MiniMax H3 Max Lip Sync in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/minimax-h3-max-lip-sync.md. Help me connect the FlyMy.AI MCP to this assistant, then run MiniMax H3 Max Lip Sync (flymyai/minimax-h3-max-lip-sync) for this task: Make the person in my photo say the words in my audio file with MiniMax H3 Max Lip Sync.
What MiniMax H3 Max Lip Sync does
Send image, a photo, an illustration or a character whose aspect ratio is between 0.4 and 2.5, and audio, a WAV, MP3 or M4A file of 5 to 60 seconds (at most 30 at 2K on FlyMy.AI). The mouth follows the sound, the video is exactly as long as the audio and the audio is its soundtrack. resolution is 480P, 768P (the default), 1080P or 2K, and the video takes the supported shape nearest your picture. enable_transcription, on by default, transcribes the audio to guide the lips: turn it off for music, singing, laughter or noise, which the transcript may turn into words that were never spoken. Outputs: video, one MP4, duration and seed. Use it for presenters, explainers, voiced characters and mascots, singing and music clips and social videos.
It is billed by the seconds of the audio you send, rounded up, more at a higher resolution and for a video over 15 seconds. It does not write or voice the speech (bring a recording, or make one with a text-to-speech model), take a prompt, or re-sync the lips of an existing video (Sync Lipsync 3 and VEED Lipsync v2 do).
Use a real person's picture or voice only with their consent: using another person's image, voice or likeness without it is not allowed.
MiniMax H3 Max Lip Sync inputs
Every input of flymyai/minimax-h3-max-lip-sync as its live schema lists them. Returns video (array), duration (string), seed (string).
| Input | Type, values and default |
|---|---|
# image | file required Allowed: image file, as a URL or upload The picture with the face to animate (a photo, an illustration or a character), a link or an upload. Its aspect ratio must be between 0.4 and 2.5. Use a real person's picture only with their permission |
# audio | file required Allowed: audio file, as a URL or upload The speech or sound the mouth follows: a WAV, MP3 or M4A file of 5 to 60 seconds (at most 30 at 2K), a link or an upload. The video is as long as the audio and its length sets the price: $0.05 a second at 480P, $0.08 at 768P, $0.16 at 1080P, $0.32 at 2K, in whole seconds rounded up, times 1.2 over 15 seconds |
# resolution | string optional Allowed: 480P, 768P, 1080P, 2K Default: 768P 480P ($0.05 a second of the audio), 768P ($0.08), 1080P ($0.16) or 2K ($0.32, up to 30 seconds); the video takes the supported shape nearest your picture |
# enable_transcription | boolean optional Default: true On (the default): the audio is transcribed to guide the lips. Turn it off when the audio is mostly music, singing, laughter or noise, which a transcript may turn into words that were never spoken. No price effect |
# seed | integer optional Allowed: 0 to 2147483647 Seed for the generation; a random one is used when you leave it out |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/minimax-h3-max-lip-syncflymyai/minimax-h3-max-lip-syncflymyai/minimax-h3-max-lip-syncMiniMax H3 Max Lip Sync price
From $0.05 per second of the audio you send, rounded up, depending on resolution. A 10-second clip costs $0.80 with the default settings. A run at the default settings costs $0.80. A run costs $0.25 to $11.52, depending on audio and resolution. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
| Setting | Price |
|---|---|
| resolution 480P | $0.05 per second |
| resolution 768P | $0.08 per second |
| resolution 1080P | $0.16 per second |
| resolution 2K | $0.32 per second |
Call MiniMax H3 Max Lip Sync from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/minimax-h3-max-lip-sync",
"input": {
"image": "https://example.com/photo.jpg",
"audio": "https://example.com/voice.mp3"
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/minimax-h3-max-lip-sync/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/minimax-h3-max-lip-sync/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F "image=@photo.jpg" \
-F "audio=@voice.mp3"Questions about MiniMax H3 Max Lip Sync
Do I need a MiniMax API key for MiniMax H3 Max Lip Sync?
No. MiniMax H3 Max Lip Sync runs on FlyMy.AI's account, so you need no MiniMax key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does MiniMax H3 Max Lip Sync cost?
From $0.05 per second of the audio you send, rounded up, depending on resolution. A 10-second clip costs $0.80 with the default settings. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use MiniMax H3 Max Lip Sync in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Make the person in my photo say the words in my audio file with MiniMax H3 Max Lip Sync." Your agent reads the inputs with get_model_schema and runs flymyai/minimax-h3-max-lip-sync with run_model.
What does MiniMax H3 Max Lip Sync need as input?
MiniMax H3 Max Lip Sync requires image and audio; it also takes 3 optional inputs, each listed on this page with its allowed values and default.
Can I call MiniMax H3 Max Lip Sync from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/minimax-h3-max-lip-sync/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





