InfiniteTalk Multi Digital Human API

wavespeed-ai/infinitetalk/multi

InfiniteTalk Multi converts a single image and two audio inputs into multi-character talking or singing videos at up to 720p. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Talking Avatar
Input

Drag & drop or click to upload

preview

Drag & drop or click to upload

Drag & drop or click to upload

Idle

$0.03per run·~33 / $1

ExamplesView all

Related Models

README

InfiniteTalk Multi

What is InfiniteTalk?

InfiniteTalk creates videos with accurate lip sync while matching head, face, and body movements to the audio. It maintains identity across unlimited-length videos and also allows image-to-video creation, transforming static photos into lively speaking or singing videos.

Why it looks great

  • Accurate lip synchronization: aligns lip motion precisely with audio, preserving natural rhythm and pronunciation.

  • Full-body coherence: captures head movements, facial expressions, and posture changes beyond the lips.

  • Identity preservation: maintains consistent facial identity and visual style across frames.

  • Image-to-video capability: turns static photos into realistic speaking or singing videos.

  • Instruction following: accepts text prompts to control scene, pose, or behavior while syncing to audio.

Pricing

Billing duration: Input media duration is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter inputs are billed as 3 seconds. Billing is capped at 600 seconds (10 minutes).

The price depends on the output resolution, the speaking order, and the length of the left and right audio files. With order meanwhile, both people speak at the same time, so the longer of the two audio files sets the billed length. With order left_right or right_left, the two audio files play one after the other, so their lengths add up.

Order meanwhile, left audio and right audio of the same length:

Output resolutionLeft and right audio 5 s eachLeft and right audio 30 s eachLeft and right audio 300 s each
480p$0.15$0.90$9.00
720p$0.30$1.80$18.00

Order left_right (the same applies to right_left), left audio and right audio of the same length:

Output resolutionLeft and right audio 5 s eachLeft and right audio 30 s eachLeft and right audio 300 s each
480p$0.30$1.80$18.00
720p$0.60$3.60$36.00

Billing Rules

  • Standard (480p) rate: per second of audio, with order meanwhile and left audio and right audio of 10 s each: $0.03
  • HD (720p) rate: per second of audio, with order meanwhile and left audio and right audio of 10 s each: $0.06 (double the 480p rate)
  • Minimum charge: all videos are billed for a minimum of 3 seconds. For example, with order meanwhile and left audio and right audio of 1 s each, 480p costs $0.09 and 720p costs $0.18.
  • Billing cap: to keep your costs predictable, billing is capped at 600 seconds (10 minutes). For example, with order meanwhile and left audio and right audio of 600 s each, 480p costs $18.00 and 720p costs $36.00.

How to Use

  1. Upload the left and right audio files.
  2. Upload your image (The image should clearly show two people).
  3. Select the speaking order (left to right, right to left, or meanwhile).
  4. Select the resolution (480p or 720p).
  5. Write the prompt if needed.
  6. Submit the job and download the results once they're ready.

Note

  • Max clip length per job: up to 10 minutes

  • Processing speed: approximately 10–30 seconds of wall time per 1 second of video (varies by resolution and queue load)

More Versions

Reference

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.

Infinitetalk Multi API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/infinitetalk/multi 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 Infinitetalk Multi 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",
    "left_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "right_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "order": "meanwhile",
    "resolution": "480p"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/infinitetalk/multi" \
  -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/wavespeed-ai/infinitetalk/multi";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "left_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "right_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
        "order": "meanwhile",
        "resolution": "480p"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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",
    "left_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "right_audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
    "order": "meanwhile",
    "resolution": "480p"
}

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/wavespeed-ai/infinitetalk/multi", 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)

Infinitetalk Multi API — Frequently asked questions

What is the Infinitetalk Multi API?

Infinitetalk Multi is a WaveSpeedAI model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. InfiniteTalk Multi converts a single image and two audio inputs into multi-character talking or singing videos at up to 720p. 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 Infinitetalk Multi 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/infinitetalk/multi.

How much does Infinitetalk Multi cost per run or per second?

Infinitetalk Multi starts at $0.03 per run or per second. 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 Infinitetalk Multi accept?

Key inputs: `prompt`, `image`, `resolution`, `seed`, `left_audio`, `order`. 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/wavespeed-ai/infinitetalk/multi.

How long does Infinitetalk Multi take to generate?

Reported generation time on WaveSpeedAI is around 835 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.

Can I use Infinitetalk Multi outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — wavespeed-ai/infinitetalk/multi for AI agents and LLMs