by ByteDance

A portrait that speaks your audio with lifelike expression, up to 60 seconds

bytedance/omnihuman-1.5/talking-avatar
  • Up to 1080p
  • AI Avatar

About OmniHuman 1.5

A portrait that speaks your audio with lifelike expression, up to 60 seconds.

Call it with the model name bytedance/omnihuman-1.5/talking-avatar on POST /jobs/createTask, from $0.135.

Introduction

Portrait animation with directed movement

ByteDance's OmniHuman 1.5 turns a portrait and recorded speech or singing into an MP4. ByteDance says expression, gesture, and body movement respond to the recording's emotion and meaning. An optional text prompt adds instructions for visible action, expression, scene, and camera behavior.

Use bytedance/omnihuman-1.5/talking-avatar for this photo-input workflow. The recording supplies the voice and words; the endpoint does not clone a voice or read a dialogue script from the prompt. Prepare the complete audio before requesting the video.

Request fields

FieldRequirement and accepted valueDefault and effect
audio_urlRequired MP3 or WAV, up to 15 MB, lasting 1–60 seconds. Speech and singing are accepted.No default recording; duration rounds upward to whole billable seconds.
promptOptional direction, up to 2,000 characters, for movement, expression, scene, or camera.No default text is specified; adding direction does not change the rate.
resolutionOptional 720p or 1080p.1080p when omitted; both selections share one rate.

These five fields apply to the talking-avatar task. A portrait that includes the upper body and hands gives the requested gesture space in the image. There is no separate aspect-ratio field among these controls; inspect the returned composition rather than assuming an exact crop.

Choose the visible performance area

Select a sharp portrait with the face looking toward the viewer. Include the hands when a palm-up invitation or another hand gesture matters to the scene.

Keep the portrait within the image format and file-size limits. Match the direction to that portrait so the movement you intend to assess is clear: a nod, an open palm, or a smile as the line ends. Review the generated framing as well as the action.

Finish the sound before the text prompt

Listen to the entire MP3 or WAV and measure its length. ByteDance recommends recordings of 15 seconds or less for quality, although the accepted range extends to 60 seconds. Audio length determines the intended clip duration and the billable quantity, so trim any portion you do not intend to use.

Write performance instructions in prompt, leaving the dialogue in audio_url. ByteDance lists Chinese, English, Japanese, Korean, Spanish, and Indonesian for prompt text. That list describes prompt languages; it is not a measured list of spoken languages tested here.

For a controlled comparison, reuse a seed while revising one instruction and keeping the remaining inputs steady. The seed helps isolate a change; it cannot guarantee matching video on repeated requests.

Observed gesture and framing

Our sleeper-train-stay example combined a 1024×1536 portrait of an auburn-haired woman in navy silk in a train compartment with a short invitation. The request selected 1080p and asked for a smile, an inviting hand movement, open palms, and a nod while keeping the camera steady.

In our tests, she raised one hand palm up, nodded, smiled, and spoke in sync with the recording. The result was 1248×1664 at 25 fps, lasting 6.44 seconds. The image became a 3:4 composition showing her from the waist up. The recorded observation confirms the raised hand and nod; it does not establish that every requested action or framing constraint landed exactly.

A separate 720p run paired an 832×1248 portrait with 4.55 seconds of speech. The result measured 832×1120 at 25 fps and 4.52 seconds, retaining a vertical composition. These dimensions describe two measured results, not fixed pixel dimensions promised by either resolution label.

Submit, retrieve, and retain

Tasks run asynchronously: submission returns a task identifier, and polling or a callback supplies completion information. Retrieve the MP4 after the task finishes, then watch the hand movement, face, framing, and final moment alongside the original recording.

Download an accepted clip during that window and save its input settings if you will revisit the performance.

For another OmniHuman option, review OmniHuman 2.0. InfiniteTalk and VEED Fabric 1.0 are related portrait-animation pages. Check their stated inputs and limits before choosing; our OmniHuman 1.5 runs do not establish a quality or processing-time ranking against them.

Request parameters

ParameterRequiredDescription
audio_urlYesThe voice or music track to use.
image_urlYesThe picture to start from.
promptNoDescribe what you want to make.
resolutionNoChoose an available output size. 720p · 1080p · Default: 1080p
seedNoUse the same seed and settings for more controlled comparisons. ≥ 0 · ≤ 2147483647

Pricing

Prices are in USD and charged to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per second
Standard$0.135

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

API quick start

Call the OmniHuman 1.5 API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls are billed in USD from your PopNow balance.
  2. Send the request. POST /jobs/createTask with model bytedance/omnihuman-1.5/talking-avatar and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "bytedance/omnihuman-1.5/talking-avatar",
  "input": {
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3",
    "resolution": "1080p"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

OmniHuman 1.5 API questions

How much does the OmniHuman 1.5 API cost?

OmniHuman 1.5 costs $0.135 per second. API usage is charged in USD to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for OmniHuman 1.5 in the API?

Put bytedance/omnihuman-1.5/talking-avatar for AI Avatar in the model field of POST /jobs/createTask.

What makes OmniHuman 1.5 more than a moving mouth?

It animates expression and body movement along with speech. ByteDance says these movements respond to the audio's emotion and meaning, and our train example showed a palm-up invitation with a nod and smile.

Will a written script make the portrait speak?

You need a recorded audio file. The optional prompt controls visible performance, while the uploaded speech or song supplies the voice; OmniHuman 1.5 does not clone voices.

Is a full minute of audio accepted?

The accepted audio range is 1–60 seconds. ByteDance recommends 15 seconds or less for quality, and our measured examples are short spoken clips rather than a full-minute validation.

What portrait and audio formats should I prepare?

Prepare JPEG, PNG, or WebP for the image and MP3 or WAV for the recording. The image limit is 30 MB and the audio limit is 15 MB; favor a frontal face and visible hands when directing gestures.

Will the output keep my portrait crop exactly?

An exact crop is not guaranteed by our examples. The train input measured 1024×1536, while its output measured 1248×1664 with a 3:4 composition showing the speaker from the waist up.

What are the limits of the OmniHuman 1.5 API?

Resolutions: 720p · 1080p; Prompt length (characters): 2,000; Largest upload: 30 MB. Requests outside these limits are rejected before anything is charged.

Can I try OmniHuman 1.5 without writing code?

Run OmniHuman 1.5 in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All OmniHuman models

More about OmniHuman 1.5