GPT Image 2.5 is LIVE — Flare & Sunburst | Try in Image Generator →

bytedance/

Seedance 2.5 Talking Avatar animates a portrait image from an audio recording to generate natural talking-avatar videos in 480P or 720P, processing up to the first 120 seconds of audio for digital human, presenter, dubbing, and avatar workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

digital-human
Input
Enable Safety Checker

Idle

$1.1per run

ExamplesView all

Present the plain unbranded moisturizer jar at chest height while speaking to the camera with a warm, confident smile. Use subtle natural hand gestures, keep the jar visible and its packaging unchanged, and never cover the face. No brand names, logos, text overlays or scene changes.

Related Models

README

Seedance 2.5 Talking Avatar

Turn a portrait and a voice recording into a talking-avatar video. Use Seedance 2.5 to create virtual presenters, product demonstrations, explainers, and spoken social content in 480p or 720p, with up to two minutes of audio per request.

Only an image and audio are required. Add an optional prompt when you want to guide the presenter's expression, movement, or product presentation.

What You Can Create

  • Virtual presenters: introduce a topic, welcome an audience, or narrate an announcement.
  • Product demonstrations: animate a presenter holding a product while delivering your recorded pitch.
  • Educational explainers: pair a consistent portrait with lesson or training audio.
  • Social videos: turn short voice recordings into on-camera messages.

How to Use

  1. Choose an image. Use a clear portrait with an unobstructed face. For a product demonstration, include the product in the image and keep it below the face.
  2. Provide the audio. Upload the speech you want to use. The model processes the first 120 seconds; longer recordings are accepted and trimmed automatically.
  3. Add direction if needed. Leave prompt empty for natural speaking behavior, or describe the expression and movement you want.
  4. Choose a resolution. 720p is the default; choose 480p for lower-cost previews.
  5. Generate the video. API requests are asynchronous. Poll the prediction result endpoint until the video URL is available.

Parameters

ParameterRequiredDescription
imageYesURL of the portrait image to animate.
audioYesURL of a nonempty speech recording. Only the first 120 seconds are processed.
promptNoOptional guidance for expression, movement, or presentation. Leave empty for natural speaking behavior.
resolutionNo480p or 720p. Default: 720p.

The output duration follows the processed audio, up to 120 seconds. Audio guides the voice, words, and speaking pace; the generated audio can differ from the original recording.

Prompt Examples

Keep directions focused on visible behavior. The audio supplies the spoken message.

Friendly introduction

Speak to the camera with a warm expression, subtle head movement, and natural blinking.

Product presentation

Present the plain moisturizer jar at chest height while speaking. Keep the product visible and its packaging unchanged. Use small, natural hand gestures without covering the face.

Calm explainer

Maintain a calm, attentive expression and steady posture while explaining the topic. Keep the camera fixed.

Tips for Better Results

  • Start with one clearly visible speaker, good lighting, and a face directed toward the camera.
  • Use clean speech with limited background noise and music.
  • Keep the mouth visible; place products and hands below the face.
  • Use an image that already matches the intended scene, clothing, and product.
  • Prefer subtle movement directions for a consistent presentation.

Pricing

Charges are based on the processed audio duration, rounded up to whole seconds, with a 4-second minimum and a 120-second maximum.

ResolutionPer billable audio second10 seconds60 seconds120 seconds
480p$0.22$2.20$13.20$26.40
720p$0.44$4.40$26.40$52.80

For example, 2.8 seconds is billed as 4 seconds, and 4.01 seconds is billed as 5 seconds. A 130-second recording is processed and billed for only the first 120 seconds. Automatic segmentation and recovery do not add separate charges.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Seedance 2.5 Talking Avatar API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/talking-avatar with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Seedance 2.5 Talking Avatar below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "resolution": "720p"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/talking-avatar" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/talking-avatar";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "resolution": "720p"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "resolution": "720p"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/talking-avatar", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Seedance 2.5 Talking Avatar API — Frequently asked questions

What is the Seedance 2.5 Talking Avatar API?

Seedance 2.5 Talking Avatar is a ByteDance model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. Seedance 2.5 Talking Avatar animates a portrait image from an audio recording to generate natural talking-avatar videos in 480P or 720P, processing up to the first 120 seconds of audio for digital human, presenter, dubbing, and avatar workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Seedance 2.5 Talking Avatar API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedance-2.5-talking-avatar.

How much does Seedance 2.5 Talking Avatar cost per run?

Seedance 2.5 Talking Avatar starts at $1.10 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Seedance 2.5 Talking Avatar accept?

Key inputs: `prompt`, `image`, `audio`, `resolution`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedance-2.5-talking-avatar.

How do I get started with the Seedance 2.5 Talking Avatar API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Seedance 2.5 Talking Avatar outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.