Alibaba Cloud / EMO

EMO v1

Retired portrait animation model that combined an image, speech audio and detected regions into an expressive video.

Video generation

retiredClosed weightsVideo generation

Official documentation (opens in a new tab)Reviewed 14 Oct 2026
24 of 33 specification fields collected

Output resolutionNot collectedAwaiting source review

Clip durationNot collectedAwaiting source review

Input billingSee ratesAlibaba Model Studio · Beijing · retired

Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit: Not collected
Maximum input tokens: Not collected
Maximum output: Not collected
Input modalities: Image, AudioSource for Input modalities (opens in a new tab)
Output modalities: VideoSource for Output modalities (opens in a new tab)
Reasoning: Not collected
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Streaming: Not collected
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Knowledge cutoff: Not collected
Release date: 2024-11-07Source for Release date (opens in a new tab)
Parameters: Not collected
Architecture: Not collected
Languages: Not collected
Context caching: Not supportedSource for Context caching (opens in a new tab)
API aliases: emo-v1Source for API aliases (opens in a new tab)
Published availability regions: China (Beijing)Source for Published availability regions (opens in a new tab)
Required request fields: image_url, audio_url, face_bbox and ext_bbox obtained from EMO detectionSource for Required request fields (opens in a new tab)
Recommended replacement: wan2.7-r2vSource for Recommended replacement (opens in a new tab)
Usage metering: Historical generated-video seconds by aspect ratioSource for Usage metering (opens in a new tab)
Output billing: Historical price per second of generated videoSource for Output billing (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Console model playground: Not supportedSource for Console model playground (opens in a new tab)
Image input limits: Portrait sides from 400 to 7,000 pixels; public HTTP(S) URLSource for Image input limits (opens in a new tab)
Audio duration limits: Up to 60 secondsSource for Audio duration limits (opens in a new tab)
Maximum audio file: 15 MBSource for Maximum audio file (opens in a new tab)
audioInputFormats: WAV, MP3Source for audioInputFormats (opens in a new tab)
Asynchronous generation: SupportedSource for Asynchronous generation (opens in a new tab)
Request mode: Historical asynchronous job submission, followed by GET /api/v1/tasks/{task_id}.Source for Request mode (opens in a new tab)
Face and motion regions: face_bbox and ext_bbox contain the detected face and animation region. Both are required for generation.Source for Face and motion regions (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Alibaba Model Studio · Beijing · retired

Provider source (opens in a new tab)

API model ID: emo-v1
Access: Retired October 10, 2026. Historical POST https://dashscope.aliyuncs.com/api/v1/services/aigc/image2video/video-synthesis. No longer an available inference offer.
Regions: China (Beijing)
retirement: Retired October 10, 2026; inference is no longer supported.Source for retirement (opens in a new tab)
Tool calling: Not supportedSource for Tool calling (opens in a new tab)
Structured output: Not supportedSource for Structured output (opens in a new tab)
Search grounding: Not supportedSource for Search grounding (opens in a new tab)
Prefix completion: Not supportedSource for Prefix completion (opens in a new tab)
Context caching: Not supportedSource for Context caching (opens in a new tab)
Batch processing: Not supportedSource for Batch processing (opens in a new tab)
Fine-tuning: Not supportedSource for Fine-tuning (opens in a new tab)
Console model playground: Not supportedSource for Console model playground (opens in a new tab)
Published request quota: Historical card: 300 requests per minuteSource for Published request quota (opens in a new tab)
Concurrent requests: Historical guide: one running generation job; excess jobs queuedSource for Concurrent requests (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Historical EMO pricing	Generated video, 1:1 aspect ratio¹	$0.011469	second
Historical EMO pricing	Generated video, 3:4 aspect ratio¹	$0.022937	second

Rate conditions

Historical Beijing rate from a cached official guide dated September 28, 2026. Service retired October 10, 2026; not a current offer. No text-question estimate.

Pricing source (opens in a new tab)

Data & enterprise terms

Historical access only. Data retention, training use and private account policies are not collected.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Alibaba Model Studio · Beijing · retired

emo-v1

Not supported

Historical model-card flag; service is retired.

Support evidence (opens in a new tab)Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Classification inference: a separately named hosted Alibaba model with no exact released checkpoint in the reviewed EMO research repository. That repository only distributes a paper reference and demonstrations. Hosted model identity, detector architecture and any undisclosed distribution remain unverified.

Classification evidence (opens in a new tab)

Lifecycle dates

Model Studio release7 Nov 2024Source (opens in a new tab)

Retirement announced10 Jul 2026Source (opens in a new tab)

Retired from Model Studio10 Oct 2026Source (opens in a new tab)

Sources reviewed

EMO retirement notice (opens in a new tab)Reviewed 14 Oct 2026

Official EMO API reference in Alibaba repository (opens in a new tab)Reviewed 14 Oct 2026

Alibaba EMO research repository (opens in a new tab)Reviewed 14 Oct 2026

Official EMO repository file inventory (opens in a new tab)Reviewed 14 Oct 2026

Historical EMO guide and regional rates (opens in a new tab)Reviewed 14 Oct 2026

Historical EMO v1 model card (opens in a new tab)Reviewed 14 Oct 2026

Model release log (opens in a new tab)Reviewed 14 Oct 2026

Model notes

Reviewed language, retrieval, decision, speech, music, video and world-model releases, with regional prices and limits. Coverage is expanding; public-weight counterparts and unresolved API identities remain under review.

The historical card lists Image input, while the official API reference requires both portrait and speech audio. The complete request contract is retained.

Retired on October 10, 2026. Prices and request contracts are historical evidence, not current service availability. Exact architecture, parameter count, training cutoff and private checkpoint mapping remain unverified.

Check against your workload

Try representative inputs, measure task success and total cost, then check the exact endpoint’s data policy.

Read our methodology