MCP / Models / Reference video, editing and lip sync

OmniHuman 2.0 MCP: talking photo videos with no API key

ByteDance OmniHuman 2.0 turns one picture and a voice track into a video of it talking, singing or performing, as long as the audio, in 720p. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use OmniHuman 2.0Inputs and price
No API key$0.07 / sTalking videoByteDanceCommercial use
OmniHuman 2.0 sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use OmniHuman 2.0 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/bytedance-omnihuman-2-0.md. Help me connect the FlyMy.AI MCP to this assistant, then run OmniHuman 2.0 (flymyai/bytedance-omnihuman-2_0) for this task: Make the person in my photo say the words in my audio file with OmniHuman 2.0.
Open FlyMy.AIDownload brief

What OmniHuman 2.0 does

The person, cartoon character or animal in the image moves in time with the sound: lips, expressions, gestures and body. Send image and audio (WAV or MP3), and optionally a prompt that directs the scene, movement and camera. The video lasts as long as the audio, from 4 seconds to 5 minutes.

OmniHuman 2.0 inputs

Every input of flymyai/bytedance-omnihuman-2_0 as its live schema lists them. Returns video (array).

InputType, values and default
# image
file required Allowed: image file, as a URL or upload The picture to bring to life: a person, character or animal; one image, 300-6000 px per side, aspect ratio 0.4-2.5, under 30 MB
# audio
file required Allowed: audio file, as a URL or upload The voice or song that drives the video: WAV or MP3, 4-300 seconds, under 15 MB. The video is as long as the audio; billed $0.07 per second
# prompt
string optional Optional direction for the scene, movements and camera, in Chinese, English, Japanese, Korean, Spanish or Indonesian

Ask your agent

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

“Make the person in my photo say the words in my audio file with OmniHuman 2.0.”runs flymyai/bytedance-omnihuman-2_0
“Turn my mascot drawing and this jingle into a singing video with OmniHuman 2.0.”runs flymyai/bytedance-omnihuman-2_0
“Create a presenter video from my headshot and voice-over with OmniHuman 2.0, the camera slowly pushing in.”runs flymyai/bytedance-omnihuman-2_0

OmniHuman 2.0 price

$0.07 per second of video, counted in whole seconds; the video is as long as the audio (4-300 s). A run costs $0.28 to $21.00, depending on audio. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

SettingPrice
Any$0.07 per second

See usage pricing →

Call OmniHuman 2.0 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/bytedance-omnihuman-2_0",
  "input": {
    "prompt": "Keep the subject and its motion, set the scene on a beach at golden hour",
    "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/bytedance-omnihuman-2_0/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/bytedance-omnihuman-2_0/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Keep the subject and its motion, set the scene on a beach at golden hour' \
  -F "image=@photo.jpg" \
  -F "audio=@voice.mp3"

Questions about OmniHuman 2.0

Do I need a ByteDance API key for OmniHuman 2.0?

No. OmniHuman 2.0 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 OmniHuman 2.0 cost?

$0.07 per second of video, counted in whole seconds; the video is as long as the audio (4-300 s). There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

How do I use OmniHuman 2.0 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 OmniHuman 2.0." Your agent reads the inputs with get_model_schema and runs flymyai/bytedance-omnihuman-2_0 with run_model.

What does OmniHuman 2.0 need as input?

OmniHuman 2.0 requires image and audio; it also takes 1 optional input, each listed on this page with its allowed values and default.

Can I call OmniHuman 2.0 from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/bytedance-omnihuman-2_0/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

OmniHuman 2.0 in the playground →OmniHuman 2.0 guide in the docs →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.