MCP / Models / Reference video, editing and lip sync

LatentSync MCP: lip sync a video to audio with no API key

LatentSync from ByteDance syncs the lips in a video to a new audio track, end to end with audio-conditioned latent diffusion. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use LatentSyncInputs and price
No API key$0.04 / runLip syncByteDanceCommercial use
LatentSync sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use LatentSync 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/latentsync.md. Help me connect the FlyMy.AI MCP to this assistant, then run LatentSync (flymyai/latentsync) for this task: Sync the lips in my video to this voice-over with LatentSync.
Open FlyMy.AIDownload brief

What LatentSync does

Send video and audio as URLs and get the video back with lip movements matched to the speech. It works without an intermediate motion step, which keeps the mouth area sharp. It is priced per run.

LatentSync inputs

Every input of flymyai/latentsync as its live schema lists them. Returns video (array).

InputType, values and default
# video
string required
# audio
string required

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Sync the lips in my video to this voice-over with LatentSync.”runs flymyai/latentsync
“Use LatentSync to dub my product demo with the Spanish audio track I attach.”runs flymyai/latentsync
“Match the speaker's mouth in my interview clip to the new audio with LatentSync.”runs flymyai/latentsync

LatentSync price

$0.04 per run. A run at the default settings costs $0.04. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

See usage pricing →

Call LatentSync 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/latentsync",
  "input": {
    "video": "...",
    "audio": "..."
  }
}

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/latentsync/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/latentsync/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'video=...' \
  -F 'audio=...'

Questions about LatentSync

Do I need a ByteDance API key for LatentSync?

No. LatentSync runs on FlyMy.AI's account, so you need no ByteDance key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does LatentSync cost?

$0.04 per run. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

How do I use LatentSync in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Sync the lips in my video to this voice-over with LatentSync." Your agent reads the inputs with get_model_schema and runs flymyai/latentsync with run_model.

What does LatentSync need as input?

LatentSync requires video and audio; it also takes 0 optional inputs, each listed on this page with its allowed values and default.

Can I call LatentSync from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/latentsync/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

LatentSync in the playground →Model endpoints in the docs →Reference video, editing and lip sync guide →Every model on FlyMy.AI →Every MCP in the catalog →Usage pricing →

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.