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.
Entrée
Sortie
InactifVotre requête coûtera $0.03 par exécution. Avec $10, vous pouvez exécuter ce modèle environ 333 fois.
Vous pouvez continuer avec :
Exemple de code
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()Installer
Installez le package requis pour votre langage.
pip install requestsAuthentification
Toutes les requêtes API nécessitent une authentification via une clé API. Vous pouvez obtenir votre clé API depuis le tableau de bord Atlas Cloud.
export ATLASCLOUD_API_KEY="your-api-key-here"En-têtes HTTP
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}N'exposez jamais votre clé API dans du code côté client ou dans des dépôts publics. Utilisez plutôt des variables d'environnement ou un proxy backend.
Soumettre une requête
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())Soumettre une requête
Soumettez une requête de génération asynchrone. L'API renvoie un identifiant de prédiction que vous pouvez utiliser pour vérifier le statut et récupérer le résultat.
/api/v1/model/generateVideoCorps de la requête
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']}")Réponse
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Vérifier le statut
Interrogez le point de terminaison de prédiction pour vérifier le statut actuel de votre requête.
/api/v1/model/prediction/{prediction_id}Exemple d'interrogation
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)Valeurs de statut
processingLa requête est encore en cours de traitement.completedLa génération est terminée. Les résultats sont disponibles.succeededLa génération a réussi. Les résultats sont disponibles.failedLa génération a échoué. Vérifiez le champ d'erreur.Réponse terminée
{
"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"
}
}Télécharger des fichiers
Téléchargez des fichiers vers le stockage Atlas Cloud et obtenez une URL utilisable dans vos requêtes API. Utilisez multipart/form-data pour le téléchargement.
/api/v1/model/uploadMediaExemple de téléchargement
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}")Réponse
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Schema d'entrée
Les paramètres suivants sont acceptés dans le corps de la requête.
Aucun paramètre disponible.
Exemple de corps de requête
{
"model": "atlascloud/infinitetalk"
}Schema de sortie
L'API renvoie une réponse de prédiction avec les URL des résultats générés.
Exemple de réponse
{
"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 intègre plus de 300 modèles d'IA directement dans votre assistant de codage IA. Une seule commande pour installer, puis utilisez le langage naturel pour générer des images, des vidéos et discuter avec des LLM.
Clients pris en charge
Installer
npx skills add AtlasCloudAI/atlas-cloud-skillsConfigurer la clé API
Obtenez votre clé API depuis le tableau de bord Atlas Cloud et définissez-la comme variable d'environnement.
export ATLASCLOUD_API_KEY="your-api-key-here"Fonctionnalités
Une fois installé, vous pouvez utiliser le langage naturel dans votre assistant IA pour accéder à tous les modèles Atlas Cloud.
Serveur MCP
Le serveur MCP Atlas Cloud connecte votre IDE avec plus de 300 modèles d'IA via le Model Context Protocol. Compatible avec tout client compatible MCP.
Clients pris en charge
Installer
npx -y atlascloud-mcpConfiguration
Ajoutez la configuration suivante au fichier de paramètres MCP de votre IDE.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Outils disponibles
Schéma API
Schéma non disponibleVeuillez vous connecter pour voir l'historique des requêtes
Vous devez vous connecter pour accéder à l'historique de vos requêtes de modèle.
Se ConnecterInfiniteTalk: 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.
