atlascloud/infinitetalk

audio-to-video

InfiniteTalk turns a reference portrait and audio into a realistic talking-head video with lip-sync, supporting up to 10-minute audio in 480p or 720p.

INPUT

Loading parameter configuration...

OUTPUT

Idle

Your generated videos will appear here

Configure your settings and click Run to get started

Your request will cost $0.03 per run. For $10 you can run this model approximately 333 times.

Here's what you can do next:

Seedance 2.0 Kling v3 Vidu Wan2.7

Parameters

Code Example
import requests
import time

# Step 1: Start video generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "atlascloud/infinitetalk",
    "prompt": "A beautiful sunset over the ocean with gentle waves",
    "width": 512,
    "height": 512,
    "duration": 3,
    "fps": 24,
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] in ["completed", "succeeded"]:
            print("Generated video:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

video_url = check_status()

Install

Install the required package for your language.

bash

pip install requests

Authentication

All API requests require authentication via an API key. You can get your API key from the Atlas Cloud dashboard.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP Headers

python

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

Keep your API key secure

Never expose your API key in client-side code or public repositories. Use environment variables or a backend proxy instead.

Submit a request

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "prompt": "A beautiful landscape"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Submit a Request

Submit an asynchronous generation request. The API returns a prediction ID that you can use to check the status and retrieve the result.

POST/api/v1/model/generateVideo

Request Body

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "atlascloud/infinitetalk",
    "input": {
        "prompt": "A beautiful sunset over the ocean with gentle waves"
    }
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")

Response

{
  "id": "pred_abc123",
  "status": "processing",
  "model": "model-name",
  "created_at": "2025-01-01T00:00:00Z"
}

Check Status

Poll the prediction endpoint to check the current status of your request.

GET/api/v1/model/prediction/{prediction_id}

Polling Example

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

Status Values

processingThe request is still being processed.

completedGeneration is complete. Outputs are available.

succeededGeneration succeeded. Outputs are available.

failedGeneration failed. Check the error field.

Completed Response

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.mp4"
    ],
    "metrics": {
      "predict_time": 45.2
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

Upload Files

Upload files to Atlas Cloud storage and get a URL you can use in your API requests. Use multipart/form-data to upload.

POST/api/v1/model/uploadMedia

Upload Example

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

Response

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Input Schema

The following parameters are accepted in the request body.

Total: 0Required: 0Optional: 0

No parameters available.

Example Request Body

json

{
  "model": "atlascloud/infinitetalk"
}

Output Schema

The API returns a prediction response with the generated output URLs.

idstringrequired

Unique identifier for the prediction.

statusstringrequired

Current status of the prediction.

processingcompletedsucceededfailed

modelstringrequired

The model used for generation.

outputsarray[string]

Array of output URLs. Available when status is "completed".

errorstring

Error message if status is "failed".

metricsobject

Performance metrics.

predict_timenumber

Time taken for video generation in seconds.

created_atstringrequired

ISO 8601 timestamp when the prediction was created.

Format: date-time

completed_atstring

ISO 8601 timestamp when the prediction was completed.

Format: date-time

Example Response

json

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.mp4"
  ],
  "metrics": {
    "predict_time": 45.2
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills integrates 300+ AI models directly into your AI coding assistant. One command to install, then use natural language to generate images, videos, and chat with LLMs.

Supported Clients

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ supported clients

Install

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

Setup API Key

Get your API key from the Atlas Cloud dashboard and set it as an environment variable.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

Capabilities

Once installed, you can use natural language in your AI assistant to access all Atlas Cloud models.

Image GenerationGenerate images with models like Nano Banana 2, Z-Image, and more.

Video CreationCreate videos from text or images with Kling, Vidu, Veo, etc.

LLM ChatChat with Qwen, DeepSeek, and other large language models.

Media UploadUpload local files for image editing and image-to-video workflows.

Learn more

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server connects your IDE with 300+ AI models via the Model Context Protocol. Works with any MCP-compatible client.

Supported Clients

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ supported clients

Install

bash

npx -y atlascloud-mcp

Configuration

Add the following configuration to your IDE's MCP settings file.

json

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

atlas_generate_imageGenerate images from text prompts.

atlas_generate_videoCreate videos from text or images.

atlas_chatChat with large language models.

atlas_list_modelsBrowse 300+ available AI models.

atlas_quick_generateOne-step content creation with auto model selection.

atlas_upload_mediaUpload local files for API workflows.

Learn more

github.com/AtlasCloudAI/mcp-server

API Schema

Schema not available

Please log in to view request history

You need to be logged in to access your model request history.

InfiniteTalk: Audio-Driven Talking Video Generation

1. Introduction

InfiniteTalk is an audio-driven video generation model developed by AtlasCloud that transforms a single portrait image into a realistic talking-head video synchronized to any speech audio input. Built on a modified Wan2.1 I2V-14B diffusion transformer backbone with a dedicated audio cross-attention module, InfiniteTalk achieves phoneme-level lip synchronization while preserving the subject's identity, hairstyle, clothing, and background throughout the entire video.

InfiniteTalk's core innovation lies in its triple cross-attention architecture: each transformer block processes visual self-attention, text prompt cross-attention, and frame-level audio cross-attention in sequence, enabling precise per-frame audio-visual alignment. Combined with a streaming inference pipeline that processes video in overlapping segments, InfiniteTalk supports continuous video generation of up to 10 minutes from a single request — far exceeding the typical 5–15 second limit of conventional image-to-video models. The model also supports dual-person mode, animating two speakers simultaneously within the same frame using separate audio tracks and bounding box annotations.

2. Key Features & Innovations

Triple Cross-Attention Audio Conditioning: Unlike text-only conditioned video models, InfiniteTalk injects audio embeddings at every transformer block via a dedicated cross-attention layer. Audio features are extracted frame-by-frame using a Wav2Vec2 encoder, providing per-frame speech signal anchoring that drives natural mouth movements, facial micro-expressions, and head motion synchronized to the audio input.

Streaming Long-Form Video Generation: InfiniteTalk's streaming mode processes audio in overlapping clip segments with configurable motion frame overlap, automatically concatenating segments into seamless long-form video. This enables generation of minutes-long talking videos without quality degradation or identity drift — a capability not available in standard image-to-video pipelines limited to single-shot outputs.

High-Fidelity Identity Preservation: The model maintains consistent facial identity, hairstyle, clothing texture, and background composition across the entire generated video. The audio conditioning signal provides strong per-frame constraints that prevent the identity drift commonly observed in long unconditional video generation.

Dual-Person Conversation Mode: InfiniteTalk supports animating two speakers in a single scene by accepting separate audio tracks and bounding box coordinates for each person. This enables realistic conversation scenarios, interview formats, and dialogue-driven content without requiring separate generation passes or post-production compositing.

Flexible Input Modalities: The model accepts either a static portrait image or a reference video as the visual source, combined with audio in WAV or MP3 format. Text prompts provide additional guidance for expression style, posture, and behavioral nuance, giving creators fine-grained control over the generated output.

Conditional VSR Upscaling: When generating at 720p resolution with audio duration under 60 seconds, InfiniteTalk automatically routes output through a FlashVSR super-resolution pipeline, delivering enhanced visual clarity without additional user configuration or cost management.

3. Model Architecture & Technical Details

InfiniteTalk is built on the Wan2.1 I2V-14B foundation model (14 billion parameters, 480p native resolution) with custom InfiniteTalk adapter weights that introduce the audio cross-attention pathway. The audio encoder uses a Chinese-Wav2Vec2-Base model that extracts frame-aligned speech embeddings at 25 fps video rate, creating a one-to-one correspondence between audio features and generated video frames.

The inference pipeline operates in two modes. In clip mode, the model generates a single video segment of up to 81 frames (approximately 3.2 seconds at 25 fps), suitable for short-form content. In streaming mode, the model iteratively generates overlapping clips with a configurable motion frame overlap (default: 9 frames), seamlessly blending segments to produce arbitrarily long video bounded only by the input audio duration and a configurable maximum frame limit.

The diffusion process uses a configurable number of denoising steps (default: 40, tunable from 1–100) with TeaCache acceleration for improved throughput. On NVIDIA H200 hardware, each 81-frame clip requires approximately 3.5 minutes of processing time, yielding a generation-to-output ratio of roughly 10–30× depending on resolution and hardware load.

For 720p output, the system employs a two-stage pipeline: base generation at 480p followed by conditional FlashVSR 4× upscaling (target: 921,600 pixels at 25 fps), applied automatically when audio duration is 60 seconds or less.

4. Performance Highlights

InfiniteTalk addresses a specific niche — audio-driven talking-head video — that differs from general-purpose text-to-video or image-to-video models. Its performance should be evaluated primarily on lip-sync accuracy, identity consistency, and long-form stability rather than visual diversity or cinematic motion range.

Capability	InfiniteTalk	General I2V Models	Dedicated Lip-Sync Tools
Lip-sync accuracy	Phoneme-level, multi-language	N/A (no audio input)	Word-level, often English-only
Maximum duration	Up to 10 minutes (streaming)	5–15 seconds typical	30–60 seconds typical
Identity preservation	High (audio-anchored per-frame)	Moderate (drift in longer clips)	Moderate
Dual-person support	Native	Not available	Rare
Resolution	480p native, 720p with VSR	Up to 1080p	Varies
Audio input	Any language WAV/MP3	N/A	Usually English TTS

InfiniteTalk achieves strong lip-sync fidelity across Chinese, English, Japanese, and other languages tested, owing to the language-agnostic Wav2Vec2 audio feature extraction. Identity drift is minimal even in 5+ minute generations due to the per-frame audio conditioning anchor.

5. Intended Use & Applications

Digital Avatar & Virtual Presenter: Create realistic talking-head videos for virtual hosts, AI assistants, and digital spokespersons using a single photo and recorded or synthesized speech audio.

Video Dubbing & Localization: Generate lip-synced video from translated audio tracks, enabling cost-effective multilingual content adaptation without re-filming or manual lip-sync editing.

Online Education & Training: Produce instructor-led video content at scale from lecture audio recordings and a single instructor photograph, reducing video production costs for e-learning platforms.

Podcast & Interview Visualization: Transform audio-only podcast or interview recordings into engaging video content with realistic speaker animations, suitable for social media distribution.

Customer Service & Chatbot Video: Generate personalized video responses driven by TTS audio output, enabling human-like video communication in automated customer interaction flows.

Social Media Content at Scale: Rapidly produce talking-head content for influencer accounts, news summaries, or commentary formats using text-to-speech pipelines combined with InfiniteTalk video generation.