Alibabacloud Video Translation

Video Translation Skill

One-click video translation powered by Alibaba Cloud IMS, supporting subtitle-level and speech-level translation.

---

Input Format Requirements

IMPORTANT: Different APIs use different address formats!

API Address Format Reference

Key: Subtitle extraction uses oss://, video translation uses HTTP URL!

User Input Handling

Format Conversion Rules

oss:// format ⇄ HTTP URL format

oss://my-bucket/videos/test.mp4
    ⇄
https://my-bucket.oss-cn-shanghai.aliyuncs.com/videos/test.mp4

Conversion Formula:

• oss://<bucket>/<path> → https://<bucket>.oss-<region>.aliyuncs.com/<path>
• HTTP URL does not require signing, use Bucket domain format directly

Local Video Processing Flow

User provides local video path
    │
    ├─ AskUserQuestion: "Please provide OSS upload path (format: oss://<bucket>/<path>/<filename>.mp4)"
    │
    ├─ User specifies upload path
    │   ├─ Check if Bucket exists
    │   ├─ Upload file: aliyun oss cp <local_path> <oss_path>
    │   ├─ Save oss:// format → for subtitle extraction
    │   └─ Save HTTP URL format → for video translation
    │
    └─ User does not specify path → STOP, user MUST provide upload path

Upload Command:

aliyun oss cp <local_path> oss://<bucket>/<path>/<filename>.mp4

Save both formats after upload:

Local: /Users/demo/videos/test.mp4
Uploaded to: oss://my-bucket/videos/test.mp4
    ├─ oss:// format: oss://my-bucket/videos/test.mp4 (for subtitle extraction)
    └─ HTTP URL: https://my-bucket.oss-cn-shanghai.aliyuncs.com/videos/test.mp4 (for video translation)

---

Execution Gate Checklist

Strict Requirement: Agent MUST execute in phase order, cannot proceed without passing current phase!

Phase 0: Environment and Credential Check (HARD-GATE)

HARD-GATE: Cannot proceed with any subsequent operations without passing!

---

Phase 1: Translation Mode Confirmation (BLOCKING)

AskUserQuestion: "Do you need subtitle translation (translate subtitles only) or speech translation (translate subtitles + replace voiceover)?"

┌─ Subtitle translation → NeedSpeechTranslate: false
└─ Speech translation → NeedSpeechTranslate: true

⚠️ No reply received → STOP, cannot proceed!

DO NOT infer translation mode from input type!

---

Phase 2: Subtitle Processing Confirmation (BLOCKING)

AskUserQuestion: "Do you need to erase original subtitles from the video? Do you need to burn-in translated subtitles?"

⚠️ No reply received → STOP, cannot proceed!

Parameter Mapping:

---

Phase 3: Output Path Confirmation (Non-blocking)

Default Output Rules:

• Bucket: Same bucket as input video
• Directory: Same directory as input video
• Filename: {source}_translated_{random8}.mp4
• Example: oss://bucket/videos/demo.mp4 → oss://bucket/videos/demo_translated_a1b2c3d4.mp4

DO NOT use shell variables, use Python: python3 -c "import random; print(''.join(random.choices('abcdefghijkmnpqrstuvwxyz23456789', k=8)))"

---

Phase 4: Subtitle Review Confirmation (Conditional Blocking)

CRITICAL: After subtitle extraction, MUST output content as-is for user review, DO NOT change format!

---

Scenario Entry Selector

Key Points:

1. When user inputs local video, MUST first upload to OSS and get HTTP URL

2. When user does not provide subtitle, MUST ask if subtitle extraction and review is needed

User inputs video
    │
    ├─ Local video?
    │   └─ Yes → AskUserQuestion: "Please provide OSS upload path"
    │       ├─ User provides path → Upload to OSS → Convert to HTTP URL → Continue
    │       └─ User does not provide → STOP
    │
    ├─ oss:// format?
    │   └─ Yes → Inform user to convert to HTTP URL format
    │
    └─ HTTP URL format? → Continue
        │
        ├─ User provides SRT file?
        │   ├─ Yes → Input type = with_subtitle
        │   │   ├─ Translation mode = speech → 【Scenario 4】 ⚠️ MUST ask CustomSrtType
        │   │   └─ Translation mode = subtitle → 【Scenario 3】
        │   │
        │   └─ No → Input type = only_video ⚠️ MUST ask if review needed
        │       │
        │       ├─ AskUserQuestion: "Do you need to extract subtitles for review first, or translate directly?"
        │       │
        │       ├─ Need review → 【Scenario 2】 ⚠️ Phase 4 blocking
        │       │
        │       └─ Direct translation → 【Scenario 1】 (TextSource=OCR_ASR)

Scenario 0 (Local video) detailed flow:

1. AskUserQuestion: "Please provide OSS upload path (format: oss://<bucket>/<path>/<filename>.mp4)"

2. After user specifies path, execute aliyun oss cp <local_path> <oss_path>

3. Convert to HTTP URL: https://<bucket>.oss-<region>.aliyuncs.com/<path>/<filename>.mp4

4. Continue with subsequent scenario flow

Scenario 2 detailed flow:

1. Ask for subtitle detection region (roi parameter)

2. Call CaptionExtraction to extract subtitles, input and output use oss:// format

3. Output subtitle content as-is for user review

4. After user confirmation, use reviewed SRT to submit translation

---

Parameter Decision Table

Decision Rules: Clearly define handling for each parameter, DO NOT assume arbitrarily!

TextSource Scenario Mapping:

CustomSrtType Trigger Rules:

---

Failure Protection Mechanism

HARD-GATE: After speech translation fails, DO NOT auto-switch to subtitle translation!

API Error Handling

SRT Format Repair Flow

Detect empty subtitle entries → Delete empty entries → Renumber → Upload repaired file → Inform user

See troubleshooting.md for details.

---

CLI Command Templates

IMPORTANT: Before submitting API, MUST reference [api-parameters.md](references/api-parameters.md) to confirm parameter format!

See cli-commands.md for details.

Core Commands:

# Register media asset
aliyun ice register-media-info --input-url "oss://<bucket>/<object>" --media-type video --user-agent AlibabaCloud-Agent-Skills

# Submit subtitle extraction (use OSS path)
aliyun ice submit-iproduction-job \
  --function-name CaptionExtraction \
  --input "Media=oss://<bucket>/<object> Type=OSS" \
  --biz-output "Media=oss://<bucket>/<output>.srt Type=OSS" \
  --job-params '{"lang":"ch","roi":[[0.5,1],[0,1]]}' \
  --force \
  --user-agent AlibabaCloud-Agent-Skills

# Submit video translation
aliyun ice submit-video-translation-job \
  --user-agent AlibabaCloud-Agent-Skills

CLI Format Key Points:

- Subtitle extraction uses command name submit-iproduction-job (lowercase, - separator)

- --input and --biz-output format: space-separated string "Media=... Type=OSS", NOT JSON

- --job-params format: JSON string

- MUST add --force to skip plugin parameter validation

- All ICE commands MUST add `--user-agent AlibabaCloud-Agent-Skills`

---

Documentation Reference

---

Key Constraints

• Before submitting API, MUST reference [api-parameters.md](references/api-parameters.md) to confirm parameter format
• All ICE CLI commands MUST add `--user-agent AlibabaCloud-Agent-Skills`
• Subtitle extraction (SubmitIProductionJob) uses `oss://` format
• Video translation (SubmitVideoTranslationJob) uses HTTP URL format, no signing needed
• Local videos MUST first be uploaded to OSS, user MUST provide upload path
• NeedFaceTranslate MUST be false
• SpeechTranslate and SubtitleTranslate are mutually exclusive
• InputConfig.Subtitle MUST use HTTPS format, DO NOT use oss://
• Speech translation + SRT input requires SpeechTranslate.CustomSrtType
• DO NOT infer translation mode from input type

---

Task Polling

Mandatory: MUST continuously poll task status until completion (State=Finished) or failure (State=Failed), DO NOT exit early!

Polling Logic:

Loop polling until:
  - State == "Finished" → Return result
  - State == "Failed" → Report error
  - Exceeds 30 minutes → Report TimeoutError

Prohibited: Return after single query / Skip polling and return JobId directly

Time Reference (3-minute video):

• Subtitle-level translation: 3-5 minutes
• Speech-level translation: 10-20 minutes

---

Result Retrieval

# Get media asset info
aliyun ice get-media-info --media-id "<MediaId>"

# Generate signed URL (for private Bucket)
aliyun oss sign oss://<bucket>/<object> --timeout 3600

---

End of Document

API Parameters for Video Translation

This document provides detailed parameter configuration for video translation related APIs.

---

SubmitIProductionJob (Subtitle Extraction)

Basic Parameters

Input Configuration

{
  "Type": "OSS",
  "Media": "oss://<bucket>/<object>"
}

Output Configuration

{
  "Type": "OSS",
  "Media": "oss://<bucket>/{source}-{timestamp}-{sequenceId}.srt"
}

Output Format: SRT subtitle file

Supported Placeholders:

• {source}: Input filename
• {timestamp}: Unix timestamp
• {sequenceId}: Sequence number

JobParams (CaptionExtraction)

{
  "fps": 5,
  "roi": [[0.5, 1], [0, 1]],
  "lang": "ch",
  "track": "main"
}

All parameters are optional:

---

SubmitVideoTranslationJob Parameters

InputConfig

Input parameters for video translation task, JSON format.

{
  "Type": "Video",
  "Video": "<mediaId_or_ossUrl>",
  "Subtitle": "<srt_url_or_content>"
}

OutputConfig

Output parameters for video translation task, JSON format.

{
  "MediaURL": "https://<bucket>.oss-<region>.aliyuncs.com/<object>.mp4",
  "Width": null,
  "Height": null
}

Default Output Path Rules:

>

If user does not specify output path, use the following defaults:

- Bucket: Same bucket as input video

- Path: Same directory as input video

- Filename: {source}_translated_{timestamp}.mp4

>

Example:

- Input: oss://my-bucket/videos/demo.mp4

- Default output: https://my-bucket.oss-cn-shanghai.aliyuncs.com/videos/demo_translated_1711440000.mp4

EditingConfig

Configuration parameters for video translation task, JSON format.

{
  "SourceLanguage": "zh",
  "TargetLanguage": "en",
  "NeedSpeechTranslate": false,
  "NeedFaceTranslate": false,
  "BilingualSubtitle": false,
  "SupportEditing": true,
  "TextSource": "OCR_ASR",
  "DetextArea": null,
  "SubtitleTranslate": {
    "OcrArea": "Auto",
    "SubtitleConfig": {
      "Type": "Text",
      "FontSize": 95,
      "FontColor": "#ffffff",
      "Font": "Alibaba PuHuiTi",
      "Y": 0.15,
      "TextWidth": 0.9,
      "Alignment": "Center",
      "BorderStyle": 1
    }
  }
}

Main Field Descriptions

DetextArea Parameter Details

Used to erase original subtitles from video.

Custom Erasure Area Parameters:

• x: Horizontal distance ratio of subtitle box top-left corner from video top-left, range [0, 1]
• y: Vertical distance ratio of subtitle box top-left corner from video top-left, range [0, 1]
• width: Subtitle box width ratio relative to video width, range [0, 1]
• height: Subtitle box height ratio relative to video height, range [0, 1]

Example (erase bottom 10% of video):

"DetextArea": "[[0, 0.9, 1, 0.1]]"

TextSource Parameter Details

CustomSrtType Parameter Details

Valid only when TextSource=SubtitleFile

SubtitleConfig Fields

---

Translation Mode Configuration

Important Constraints:

- This Skill only supports subtitle-level and speech-level translation, NeedFaceTranslate must be set to false

- SpeechTranslate and SubtitleTranslate cannot be set simultaneously, choose one based on translation mode

- When speech-level translation uses SRT input, must fill `SpeechTranslate.CustomSrtType`

Speech-level Translation CustomSrtType Required Rules

Mandatory: When speech-level translation (NeedSpeechTranslate=true) uses SRT file as input, must fill `SpeechTranslate.CustomSrtType`.

>

Reference: https://help.aliyun.com/zh/ims/use-cases/introduction-and-examples-of-video-translation-parameters

---

Subtitle Style Mapping

Font Size

Subtitle Position

---

Language Codes

Common Languages

For complete language list, see: Alibaba Cloud Video Translation Supported Languages

---

Complete Examples

Scenario A: Direct Translation - Subtitle-level Translation (TextSource=OCR_ASR)

{
  "InputConfig": "{\"Type\":\"Video\",\"Video\":\"oss://my-bucket.oss-cn-shanghai.aliyuncs.com/input.mp4\"}",
  "OutputConfig": "{\"MediaURL\":\"https://my-bucket.oss-cn-shanghai.aliyuncs.com/output.mp4\"}",
  "EditingConfig": "{\"SourceLanguage\":\"zh\",\"TargetLanguage\":\"en\",\"NeedSpeechTranslate\":false,\"NeedFaceTranslate\":false,\"TextSource\":\"OCR_ASR\",\"SubtitleTranslate\":{\"OcrArea\":\"Auto\",\"SubtitleConfig\":{\"Type\":\"Text\",\"FontSize\":95,\"FontColor\":\"#ffffff\",\"Font\":\"Alibaba PuHuiTi\",\"Y\":0.15}}}"
}

Scenario B: Using External SRT File (TextSource=SubtitleFile)

{
  "InputConfig": "{\"Type\":\"Video\",\"Video\":\"oss://my-bucket.oss-cn-shanghai.aliyuncs.com/input.mp4\",\"Subtitle\":\"https://my-bucket.oss-cn-shanghai.aliyuncs.com/subtitle.srt\"}",
  "OutputConfig": "{\"MediaURL\":\"https://my-bucket.oss-cn-shanghai.aliyuncs.com/output.mp4\"}",
  "EditingConfig": "{\"SourceLanguage\":\"zh\",\"TargetLanguage\":\"en\",\"NeedSpeechTranslate\":false,\"NeedFaceTranslate\":false,\"TextSource\":\"SubtitleFile\",\"CustomSrtType\":\"SourceSrt\",\"SubtitleTranslate\":{\"OcrArea\":\"Auto\",\"SubtitleConfig\":{\"Type\":\"Text\",\"FontSize\":95,\"FontColor\":\"#ffffff\",\"Font\":\"Alibaba PuHuiTi\",\"Y\":0.15}}}"
}

Speech-level Translation

{
  "InputConfig": "{\"Type\":\"Video\",\"Video\":\"oss://my-bucket.oss-cn-shanghai.aliyuncs.com/input.mp4\"}",
  "OutputConfig": "{\"MediaURL\":\"https://my-bucket.oss-cn-shanghai.aliyuncs.com/output.mp4\"}",
  "EditingConfig": "{\"SourceLanguage\":\"zh\",\"TargetLanguage\":\"en\",\"NeedSpeechTranslate\":true,\"NeedFaceTranslate\":false,\"SpeechTranslate\":{\"VoiceConfig\":{\"Voice\":\"zhiyan_emo\"}}}"
}

Speech-level Translation + SRT Input (Must fill CustomSrtType)

{
  "InputConfig": "{\"Type\":\"Video\",\"Video\":\"oss://my-bucket.oss-cn-shanghai.aliyuncs.com/input.mp4\",\"Subtitle\":\"https://my-bucket.oss-cn-shanghai.aliyuncs.com/subtitle.srt\"}",
  "OutputConfig": "{\"MediaURL\":\"https://my-bucket.oss-cn-shanghai.aliyuncs.com/output.mp4\"}",
  "EditingConfig": "{\"SourceLanguage\":\"zh\",\"TargetLanguage\":\"en\",\"NeedSpeechTranslate\":true,\"NeedFaceTranslate\":false,\"TextSource\":\"SubtitleFile\",\"SpeechTranslate\":{\"CustomSrtType\":\"SourceSrt\",\"VoiceConfig\":{\"Voice\":\"zhiyan_emo\"}}}"
}

Note:

- All modes must set NeedFaceTranslate: false

- When using TextSource=SubtitleFile, must specify Subtitle field in InputConfig

- `InputConfig.Subtitle` must use HTTPS format, `oss://` prefix is prohibited: https://<bucket>.oss-<region>.aliyuncs.com/<object>

- Speech-level translation + SRT input requires filling `SpeechTranslate.CustomSrtType`

---

Subtitle Extraction Result Format

Subtitle extraction task outputs SRT format file directly to specified OSS path.

SRT Format Example

1
00:00:00,000 --> 00:00:02,500
First sentence

2
00:00:02,500 --> 00:00:05,000
Second sentence

SRT Format Validation and Auto Repair

Mandatory: Before submitting speech translation task, must check and fix empty subtitle entries in SRT file!

Problem Cause: InputConfig.Subtitle is invalid error is usually caused by SRT containing empty subtitle entries:

3
00:00:08,000 --> 00:00:10,600

4
00:00:10,600 --> 00:00:12,000
This is a normal subtitle

Entry 3 above has only sequence number and timeline, no content, does not conform to SRT specification.

Processing Flow: 1. Check SRT file, find all empty subtitle entries 2. Auto-delete empty subtitle entries, renumber 3. Inform user: "Detected X empty subtitle entries, auto-deleted and renumbered" 4. Upload repaired SRT file

---

Error Handling

Common Error Codes

Subtitle Extraction Failed

Extraction failed → Request user to provide SRT file

Language Detection Failed

Analyze extracted result characters:
- Contains Chinese characters → zh
- Contains Japanese characters → ja
- Contains Korean characters → ko
- Mainly English → en
- Cannot determine → Ask user

Speech Translation Failed Handling

Mandatory: After speech translation fails, DO NOT auto-switch to subtitle translation, must confirm with user first!

>

Use AskUserQuestion tool to ask user:

- "Speech translation failed, error message: {ErrorMessage}. Do you want to try switching to subtitle translation mode?"

---

Limits and Constraints

CLI Command Templates

This document provides ready-to-use CLI command templates.

---

Environment Check

# Check CLI version
aliyun version

# Check credential configuration
aliyun sts GetCallerIdentity

# Check ICE plugin
aliyun ice help

---

Media Registration

aliyun ice register-media-info \
  --input-url "oss://<bucket>/<object>" \
  --media-type video \
  --user-agent AlibabaCloud-Agent-Skills

Returns: MediaId

---

Subtitle Extraction (CaptionExtraction)

CLI Format Key: Use command name submit-iproduction-job + --force

Method 1: Using OSS Path

aliyun ice submit-iproduction-job \
  --function-name CaptionExtraction \
  --input "Media=oss://<bucket>/<object> Type=OSS" \
  --biz-output "Media=oss://<bucket>/<output>.srt Type=OSS" \
  --job-params '{"lang":"ch","roi":[[0.5,1],[0,1]]}' \
  --name "<task_name>" \
  --force \
  --user-agent AlibabaCloud-Agent-Skills

Method 2: Using MediaId (Registered Media)

aliyun ice submit-iproduction-job \
  --function-name CaptionExtraction \
  --input "Media=<mediaId> Type=MediaId" \
  --biz-output "Media=oss://<bucket>/<output>.srt Type=OSS" \
  --job-params '{"lang":"ch","roi":[[0.5,1],[0,1]]}' \
  --name "<task_name>" \
  --force \
  --user-agent AlibabaCloud-Agent-Skills

CLI Format Notes:

• Use command name: submit-iproduction-job (lowercase, - separator)
• Use lowercase parameter names: --function-name, --input, --biz-output, --job-params
• `--input` and `--biz-output` format: space-separated string "Media=... Type=OSS", NOT JSON
• `--job-params` format: JSON string
• Add --force to skip plugin parameter validation
• `--job-params` is required, must include roi parameter

JobParams Parameters:

{
  "fps": 5,
  "roi": [[0.5, 1], [0, 1]],
  "lang": "ch",
  "track": "main"
}

---

Query Subtitle Extraction Task

aliyun ice QueryIProductionJob \
  --JobId "<job_id>" \
  --force \
  --user-agent AlibabaCloud-Agent-Skills

---

Submit Video Translation Task

CLI Format Key: JSON format parameters + --region to specify service region

Mode 1: Subtitle-level Translation

aliyun ice submit-video-translation-job \
  --input-config '{"Type":"Video","Video":"https://<bucket>.oss-<region>.aliyuncs.com/<object>.mp4"}' \
  --output-config '{"MediaURL":"https://<bucket>.oss-<region>.aliyuncs.com/<output>.mp4"}' \
  --editing-config '{"SourceLanguage":"zh","TargetLanguage":"en","NeedSpeechTranslate":false,"NeedFaceTranslate":false,"TextSource":"OCR_ASR","SubtitleTranslate":{"OcrArea":"Auto","SubtitleConfig":{"Type":"Text","FontSize":48,"FontColor":"#ffffff","Font":"STHeiti","Y":0.15}}}' \
  --title "<task_title>" \
  --region <region> \
  --user-agent AlibabaCloud-Agent-Skills

Mode 2: Speech-level Translation

aliyun ice submit-video-translation-job \
  --input-config '{"Type":"Video","Video":"https://<bucket>.oss-<region>.aliyuncs.com/<object>.mp4"}' \
  --output-config '{"MediaURL":"https://<bucket>.oss-<region>.aliyuncs.com/<output>.mp4"}' \
  --editing-config '{"SourceLanguage":"zh","TargetLanguage":"en","NeedSpeechTranslate":true,"NeedFaceTranslate":false,"SpeechTranslate":{"VoiceConfig":{"Voice":"zhiyan_emo"}}}' \
  --title "<task_title>" \
  --region <region> \
  --user-agent AlibabaCloud-Agent-Skills

Mode 3: Using External SRT File

Key: InputConfig.Subtitle must use HTTPS format, oss:// prefix is prohibited

aliyun ice submit-video-translation-job \
  --input-config '{"Type":"Video","Video":"https://<bucket>.oss-<region>.aliyuncs.com/<object>.mp4","Subtitle":"https://<bucket>.oss-<region>.aliyuncs.com/<subtitle>.srt"}' \
  --output-config '{"MediaURL":"https://<bucket>.oss-<region>.aliyuncs.com/<output>.mp4"}' \
  --editing-config '{"SourceLanguage":"zh","TargetLanguage":"en","NeedSpeechTranslate":false,"NeedFaceTranslate":false,"TextSource":"SubtitleFile","CustomSrtType":"SourceSrt","SubtitleConfig":{"Type":"Text","FontSize":48,"FontColor":"#ffffff","Font":"STHeiti","Y":0.15}}' \
  --title "<task_title>" \
  --region <region> \
  --user-agent AlibabaCloud-Agent-Skills

EditingConfig Core Fields:

---

Query Video Translation Task

aliyun ice get-smart-handle-job \
  --job-id "<job_id>" \
  --user-agent AlibabaCloud-Agent-Skills

Polling Recommendation: Query every 30 seconds, timeout 30 minutes

---

OSS Commands

Note: OSS commands do not support --user-agent

Local Video Upload

# Upload local video to OSS
aliyun oss cp <local_path> oss://<bucket>/<path>/<filename>.mp4

# Example
aliyun oss cp /Users/demo/videos/test.mp4 oss://my-bucket/videos/test.mp4

OSS URL Format Reference

Important: Different APIs use different address formats!

Key: Subtitle extraction uses oss://, video translation uses HTTP URL!

Format Conversion Rules

oss:// format ⇄ HTTP URL format

oss://my-bucket/videos/test.mp4
    ⇄
https://my-bucket.oss-cn-shanghai.aliyuncs.com/videos/test.mp4

Conversion Formula: oss://<bucket>/<path> → https://<bucket>.oss-<region>.aliyuncs.com/<path>

Other OSS Commands

# List files
aliyun oss ls oss://<bucket>/<prefix>

# Download file
aliyun oss cp oss://<bucket>/<object> <local_path>

# Generate signed URL (for result sharing, required for private Bucket)
aliyun oss sign oss://<bucket>/<object> --timeout 3600

---

Command Quick Reference

Aliyun CLI Installation & Configuration Guide

Complete guide for installing and configuring Aliyun CLI.

Aliyun CLI 3.3.1+: Supports installing and using all published Alibaba Cloud product plugins. Make sure to upgrade to 3.3.1 or later for full plugin ecosystem coverage.

Installation

macOS

Using Homebrew (Recommended)

brew install aliyun-cli
# Upgrade to latest
brew upgrade aliyun-cli

# Verify version (>= 3.3.1)
aliyun version

Using Binary

# Download
wget https://aliyuncli.alicdn.com/aliyun-cli-macosx-latest-amd64.tgz

# Extract
tar -xzf aliyun-cli-macosx-latest-amd64.tgz

# Move to PATH
sudo mv aliyun /usr/local/bin/

# Verify
aliyun version

Linux

Debian/Ubuntu

# Download
wget https://aliyuncli.alicdn.com/aliyun-cli-linux-latest-amd64.tgz

# Extract and install
tar -xzf aliyun-cli-linux-latest-amd64.tgz
sudo mv aliyun /usr/local/bin/

# Verify
aliyun version

CentOS/RHEL

# Download
wget https://aliyuncli.alicdn.com/aliyun-cli-linux-latest-amd64.tgz

# Extract and install
tar -xzf aliyun-cli-linux-latest-amd64.tgz
sudo mv aliyun /usr/local/bin/

# Verify
aliyun version

ARM64 Architecture

# Download ARM64 version
wget https://aliyuncli.alicdn.com/aliyun-cli-linux-latest-arm64.tgz

# Extract and install
tar -xzf aliyun-cli-linux-latest-arm64.tgz
sudo mv aliyun /usr/local/bin/

Windows

Using Binary 1. Download from: https://aliyuncli.alicdn.com/aliyun-cli-windows-latest-amd64.zip 2. Extract the ZIP file 3. Add the directory to your PATH environment variable 4. Open new Command Prompt or PowerShell 5. Verify: aliyun version

Using PowerShell

# Download
Invoke-WebRequest -Uri "https://aliyuncli.alicdn.com/aliyun-cli-windows-latest-amd64.zip" -OutFile "aliyun-cli.zip"

# Extract
Expand-Archive -Path aliyun-cli.zip -DestinationPath C:\aliyun-cli

# Add to PATH (requires admin privileges)
$env:Path += ";C:\aliyun-cli"
[Environment]::SetEnvironmentVariable("Path", $env:Path, [System.EnvironmentVariableTarget]::Machine)

# Verify
aliyun version

Configuration

Quick Start

aliyun configure set \
  --mode AK \
  --access-key-id <your-access-key-id> \
  --access-key-secret <your-access-key-secret> \
  --region cn-hangzhou

All aliyun configure commands support non-interactive flags, which is the recommended approach — it works in scripts, CI/CD pipelines, and agent-driven automation without hanging on stdin prompts.

Where to Get Access Keys

1. Log in to Aliyun Console: https://ram.console.aliyun.com/ 2. Navigate to: AccessKey Management 3. Create a new AccessKey pair 4. Save the secret immediately — it's only shown once

Configuration Modes

Aliyun CLI supports 6 authentication modes. All examples below use non-interactive flags.

1. AK Mode (Access Key)

Most common mode for personal accounts and scripts.

aliyun configure set \
  --mode AK \
  --access-key-id LTAI5tXXXXXXXX \
  --access-key-secret 8dXXXXXXXXXXXXXXXXXXXXXXXX \
  --region cn-hangzhou

Configuration is stored in ~/.aliyun/config.json:

{
  "current": "default",
  "profiles": [
    {
      "name": "default",
      "mode": "AK",
      "access_key_id": "LTAI5tXXXXXXXX",
      "access_key_secret": "8dXXXXXXXXXXXXXXXXXXXXXXXX",
      "region_id": "cn-hangzhou",
      "output_format": "json",
      "language": "en"
    }
  ]
}

2. StsToken Mode (Temporary Credentials)

For short-lived access (tokens expire in 1-12 hours).

aliyun configure set \
  --mode StsToken \
  --access-key-id LTAI5tXXXXXXXX \
  --access-key-secret 8dXXXXXXXXXXXXXXXXXXXXXXXX \
  --sts-token v1.0:XXXXXXXXXXXXXXXX \
  --region cn-hangzhou

Use cases: CI/CD pipelines, temporary access for external contractors, cross-account access.

3. RamRoleArn Mode (Assume RAM Role)

Assume a RAM role for elevated or cross-account access.

aliyun configure set \
  --mode RamRoleArn \
  --access-key-id LTAI5tXXXXXXXX \
  --access-key-secret 8dXXXXXXXXXXXXXXXXXXXXXXXX \
  --ram-role-arn acs:ram::123456789012:role/AdminRole \
  --role-session-name my-session \
  --region cn-hangzhou

Use cases: cross-account resource access, temporary elevated privileges, role-based access control.

4. EcsRamRole Mode (ECS Instance RAM Role)

Use the RAM role attached to an ECS instance — no credentials needed.

aliyun configure set \
  --mode EcsRamRole \
  --ram-role-name MyEcsRole \
  --region cn-hangzhou

Requirements: must be running on an ECS instance with a RAM role attached.

Use cases: scripts and automation running on ECS instances.

5. RsaKeyPair Mode (RSA Key Pair)

Use RSA key pair for authentication (generate key pair in Aliyun Console first).

aliyun configure set \
  --mode RsaKeyPair \
  --private-key /path/to/private-key.pem \
  --key-pair-name my-key-pair \
  --region cn-hangzhou

6. RamRoleArnWithEcs Mode (ECS + RAM Role)

Combine ECS instance role with RAM role assumption for cross-account access from ECS.

aliyun configure set \
  --mode RamRoleArnWithEcs \
  --ram-role-name MyEcsRole \
  --ram-role-arn acs:ram::123456789012:role/TargetRole \
  --role-session-name my-session \
  --region cn-hangzhou

Environment Variables

Highest priority - overrides config file

Access Key Mode

export ALIBABA_CLOUD_ACCESS_KEY_ID=your_access_key_id
export ALIBABA_CLOUD_ACCESS_KEY_SECRET=your_access_key_secret
export ALIBABA_CLOUD_REGION_ID=cn-hangzhou

STS Token Mode

export ALIBABA_CLOUD_ACCESS_KEY_ID=your_access_key_id
export ALIBABA_CLOUD_ACCESS_KEY_SECRET=your_access_key_secret
export ALIBABA_CLOUD_SECURITY_TOKEN=your_sts_token
export ALIBABA_CLOUD_REGION_ID=cn-hangzhou

ECS RAM Role Mode

export ALIBABA_CLOUD_ECS_METADATA=role_name

Use Case:

• CI/CD pipelines
• Docker containers
• Temporary credential override

Managing Multiple Profiles

Create Named Profiles

aliyun configure set --profile projectA \
  --mode AK \
  --access-key-id LTAI5tAAAAAAAA \
  --access-key-secret 8dAAAAAAAAAAAAAAAAAAAAAAAA \
  --region cn-hangzhou

aliyun configure set --profile projectB \
  --mode AK \
  --access-key-id LTAI5tBBBBBBBB \
  --access-key-secret 8dBBBBBBBBBBBBBBBBBBBBBBBB \
  --region cn-shanghai

Use Specific Profile

aliyun ecs describe-instances --profile projectA

export ALIBABA_CLOUD_PROFILE=projectA
aliyun ecs describe-instances   # Uses projectA

List and Switch Profiles

aliyun configure list                      # List all profiles
aliyun configure set --current projectA    # Switch default profile

Credential Priority

Credentials are loaded in this order (first found wins):

1. Command-line flag: --profile <name> 2. Environment variable: ALIBABA_CLOUD_PROFILE 3. Environment credentials: ALIBABA_CLOUD_ACCESS_KEY_ID, etc. 4. Configuration file: ~/.aliyun/config.json (current profile) 5. ECS Instance RAM Role: If running on ECS with attached role

Verification

Test Authentication

# Basic test - list regions
aliyun ecs describe-regions

# Expected output: JSON array of regions

If successful, you'll see:

{
  "Regions": {
    "Region": [
      {
        "RegionId": "cn-hangzhou",
        "RegionEndpoint": "ecs.cn-hangzhou.aliyuncs.com",
        "LocalName": "华东 1（杭州）"
      },
      ...
    ]
  },
  "RequestId": "..."
}

If failed, you'll see error messages:

• InvalidAccessKeyId.NotFound - Wrong Access Key ID
• SignatureDoesNotMatch - Wrong Access Key Secret
• InvalidSecurityToken.Expired - STS token expired (for StsToken mode)
• Forbidden.RAM - Insufficient permissions

Debug Configuration

# Show current configuration
aliyun configure get

# Test with debug logging
aliyun ecs describe-regions --log-level=debug

# Check credential provider
aliyun configure get mode

Security Best Practices

1. Use RAM Users (Not Root Account)

❌ Don't: Use Aliyun root account credentials ✅ Do: Create RAM users with specific permissions

# Create RAM user in console
# Attach only necessary policies
# Use RAM user's access keys

2. Principle of Least Privilege

Grant only the minimum permissions needed:

# Example: Read-only ECS access
# Attach policy: AliyunECSReadOnlyAccess

3. Rotate Access Keys Regularly

# Create new access key in RAM Console, then update configuration
aliyun configure set --access-key-id NEW_KEY --access-key-secret NEW_SECRET
# Delete old access key from console

4. Use STS Tokens for Temporary Access

aliyun configure set --mode StsToken \
  --access-key-id XXXX --access-key-secret XXXX \
  --sts-token XXXX --region cn-hangzhou

5. Use ECS RAM Roles When Possible

aliyun configure set --mode EcsRamRole --ram-role-name MyRole --region cn-hangzhou

6. Never Commit Credentials

# Add to .gitignore
echo "~/.aliyun/config.json" >> .gitignore

# Use environment variables in CI/CD instead

7. Secure Config File

# Restrict permissions
chmod 600 ~/.aliyun/config.json

Troubleshooting

Issue: Command Not Found

# Check installation
which aliyun

# Check PATH
echo $PATH

# Reinstall or add to PATH

Issue: Authentication Failed

# Verify configuration
aliyun configure get

# Test with debug
aliyun ecs describe-regions --log-level=debug

# Check credentials in console
# Verify access key is active

Issue: Permission Denied

# Error: Forbidden.RAM

# Check RAM user permissions
# Attach necessary policies in RAM console
# Example: AliyunECSFullAccess for ECS operations

Issue: STS Token Expired

# Error: InvalidSecurityToken.Expired

# Reconfigure with new token
aliyun configure set --mode StsToken \
  --access-key-id XXXX --access-key-secret XXXX \
  --sts-token NEW_TOKEN --region cn-hangzhou

Issue: Wrong Region

# Some resources may not exist in the specified region

# Check available regions
aliyun ecs describe-regions

# Update default region
aliyun configure set region cn-shanghai

Advanced Configuration

Custom Endpoint

# Use custom or private endpoint
export ALIBABA_CLOUD_ECS_ENDPOINT=ecs-vpc.cn-hangzhou.aliyuncs.com

Proxy Settings

# HTTP proxy
export HTTP_PROXY=http://proxy.example.com:8080
export HTTPS_PROXY=http://proxy.example.com:8080

# No proxy for specific domains
export NO_PROXY=localhost,127.0.0.1,.aliyuncs.com

Timeout Settings

# Connection timeout (default: 10s)
export ALIBABA_CLOUD_CONNECT_TIMEOUT=30

# Read timeout (default: 10s)
export ALIBABA_CLOUD_READ_TIMEOUT=30

Next Steps

After installation and configuration:

1. Install plugins for services you need (v3.3.1+ supports all published product plugins):

   aliyun plugin install --names ecs vpc rds

   # List all available plugins
   aliyun plugin list-remote

2. Explore commands:

   aliyun ecs --help
   aliyun fc --help

3. Read documentation:

• Command Syntax Guide
• Global Flags Reference
• Common Scenarios

References

• Official Documentation: https://help.aliyun.com/zh/cli/
• RAM Console: https://ram.console.aliyun.com/
• Access Key Management: https://ram.console.aliyun.com/manage/ak
• Plugin Repository: https://github.com/aliyun/aliyun-cli

RAM Policies for Video Translation Skill

This document lists all RAM permissions required for the Video Translation Skill.

Permission List

ICE (Intelligent Cloud Editing) Permissions

OSS Permissions

Complete RAM Policy JSON

{
  "Version": "1",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "ice:RegisterMediaInfo",
        "ice:SubmitIProductionJob",
        "ice:QueryIProductionJob",
        "ice:GetSmartHandleJob",
        "ice:SubmitVideoTranslationJob",
        "ice:GetMediaInfo"
      ],
      "Resource": "*"
    },
    {
      "Effect": "Allow",
      "Action": [
        "oss:GetObject",
        "oss:PutObject",
        "oss:ListObjects"
      ],
      "Resource": [
        "acs:oss:*:*:<your-input-bucket>/*",
        "acs:oss:*:*:<your-output-bucket>/*"
      ]
    }
  ]
}

Permission Configuration Steps

1. Login to RAM Console 2. Create a custom permission policy, paste the JSON above (replace bucket names) 3. Grant the policy to the RAM user or role that needs to use video translation

Important Notes

• Principle of Least Privilege: Recommend limiting OSS permissions to specific buckets
• Region Restriction: If further restriction is needed, specify region in Resource
• Subscription Purchase: Even with AliyunICEFullAccess granted, if you encounter "not subscribed" error, you need to purchase a subscription package at IMS Video Translation Product Page before using the service

Troubleshooting Guide for Video Translation Skill

This document provides detailed error handling procedures for video translation task execution.

---

1. API Error Handling

1.1 Forbidden.SubscriptionRequired

Error Meaning: User has not enabled video translation service or has insufficient permissions.

Handling Flow:

Detect error → Output permission requirements → Guide user to activate service

Required Permission List:

Standard Output:

## Insufficient Permissions

You need to enable the video translation service and configure the corresponding RAM permissions.

**Required Permissions**:
- ice:RegisterMediaInfo
- ice:SubmitIProductionJob
- ice:QueryIProductionJob
- ice:GetSmartHandleJob
- ice:SubmitVideoTranslationJob
- oss:GetObject
- oss:PutObject
- oss:ListObjects

**Solution**:
1. Login to [RAM Console](https://ram.console.aliyun.com/)
2. Create a custom permission policy with the above permissions
3. Grant the policy to the current RAM user or role

**Next Step**: Re-execute the task after configuration is complete

---

1.2 InvalidParameter

Error Meaning: API parameter format error.

Handling Flow:

Detect error → Parse error details → Output correction suggestions based on table below

Common Parameter Errors:

Standard Output:

## Parameter Format Error

**Error Message**: {original error}

**Possible Causes**:
- {cause 1}
- {cause 2}

**Correction Suggestions**:
- {suggestion 1}
- {suggestion 2}

**Next Step**: Re-execute after correcting parameters

---

1.3 InputConfig.Subtitle is invalid

Error Meaning: SRT subtitle file format is invalid, usually contains empty subtitle entries.

Handling Flow: See SRT Format Repair Flow

---

1.4 JobFailed

Error Meaning: Task execution failed.

Handling Flow:

Detect error → Record JobId → Analyze failure reason → Ask user to retry or switch mode

Standard Output:

## Task Execution Failed

**JobId**: {JobId}
**Failure Reason**: {failure reason}

**Suggested Solutions**:
1. Retry task
2. Check input video format
3. Contact technical support

**Next Step**: Confirm whether to retry the task?

---

2. SRT Format Repair Flow

2.1 Problem Identification

Empty subtitle entry example:

1
00:00:00,000 --> 00:00:02,500
First sentence

2
00:00:02,500 --> 00:00:05,000
Second sentence

3
00:00:08,000 --> 00:00:10,600

4
00:00:10,600 --> 00:00:12,000
This is normal subtitle

Problem: Entry 3 has only sequence number and timeline, no subtitle content.

2.2 Repair Steps

Detect empty subtitle entries → Delete empty entries → Renumber → Upload repaired file → Inform user

2.3 Repair Command

Use Python script to auto-repair:

import re

def fix_srt(content: str) -> tuple[str, int]:
    """
    Fix empty subtitle entries in SRT file.

    Args:
        content: SRT file content

    Returns:
        (repaired content, count of removed empty entries)
    """
    # Match SRT entries: sequence + timeline + content
    pattern = r'(\d+)\n(\d{2}:\d{2}:\d{2},\d{3} --> \d{2}:\d{2}:\d{2},\d{3})\n(.*?)(?=\n\d+\n|\Z)'
    matches = re.findall(pattern, content, re.DOTALL)

    # Filter out entries with empty content
    valid_entries = [(idx, timecode, text.strip())
                     for idx, timecode, text in matches
                     if text.strip()]

    # Renumber and build new content
    result = []
    for new_idx, (_, timecode, text) in enumerate(valid_entries, 1):
        result.append(f"{new_idx}\n{timecode}\n{text}\n")

    removed_count = len(matches) - len(valid_entries)
    return '\n'.join(result), removed_count

2.4 Standard Output

## SRT File Repair

**Detection Result**: Found {count} empty subtitle entries

**Action Taken**: Auto-deleted empty entries and renumbered

**Repaired File**: {repaired OSS path}

**Next Step**: Continue task with repaired SRT file

---

3. Speech Translation Failed Handling

HARD-GATE: After speech translation fails, DO NOT auto-switch to subtitle translation mode, must ask user first!

3.1 Handling Flow

Speech translation failed → Output error message → AskUserQuestion to ask about switching → Execute after user confirmation

3.2 Prohibited Actions

• DO NOT auto-switch to subtitle translation mode
• DO NOT assume user's choice
• DO NOT skip user confirmation

3.3 Standard Inquiry

Use AskUserQuestion tool:

## Speech Translation Failed

**Error Message**: {original error}

**Available Options**:
1. Switch to subtitle translation mode (translate subtitles only, no voiceover replacement)
2. Retry speech translation
3. Terminate task

**Please Select**: How would you like to proceed?

3.4 User Choice Handling

---

4. AskUserQuestion No Response Handling

4.1 Timeout Handling Rules

4.2 30 Second Timeout Output

## Waiting for Your Response

Waiting for your confirmation to continue the task...

**Current Status**: Waiting for user to confirm translation mode
**Time Waited**: 30 seconds

Please reply when ready.

4.3 60 Second Timeout Output

## Task Paused

Task has been paused due to no response for an extended period.

**Completed Steps**:
- step 1: {step 1 description}
- step 2: {step 2 description}

**Waiting Confirmation**: {question waiting for confirmation}

**Resume**: Please reply to your question, I will continue from the current step.

---

5. Failure Message Output Template

5.1 General Template

## Task Execution Failed

**Failure Phase**: {phase name}
**Failure Type**: {type: API call failed / User confirmation timeout / Parameter error / Other}
**JobId**: {if applicable}

**Error Message**:

{original error}

**Suggested Solutions**:
- {solution 1}
- {solution 2}

**Completed Steps**:
- step 1: {step 1 description}
- step 2: {step 2 description}

**Next Step**: Re-execute after confirmation

5.2 Phase Name Reference

---

6. Common Issue Troubleshooting

6.1 Video Cannot Be Processed

6.2 Subtitle Extraction Failed

6.3 Translation Quality Issues

---

7. Error Recovery Strategy

7.1 Retryable Errors

The following errors can be auto-retried:

7.2 Non-Retryable Errors

The following errors require user intervention:

• Insufficient permissions (Forbidden.SubscriptionRequired)
• Parameter error (InvalidParameter)
• Video format not supported
• SRT format error

7.3 Retry Flow

Detect retryable error → Wait interval → Retry → Success/Failure
    ↓
Max retries reached → Output failure info → Ask user

---

End of Document

Workflow Details

This document provides detailed execution flow and timing for 4 scenarios.

---

Scenario Overview

---

Scenario 1: Direct Translation

Execution Flow

Phase 0: Environment Check → Phase 1: Translation Mode Confirmation → Phase 2: Subtitle Processing Confirmation →
Phase 3: Output Path Confirmation → Phase 5: Task Submission → Phase 6: Task Polling → Phase 7: Result Retrieval

Detailed Steps

Step 1: Environment Check (Phase 0)

• Check CLI version >= 3.3.1
• Check credential status (aliyun configure list)
• Check input video OSS file exists

Duration: ~10 seconds

Step 2: Register Media

aliyun ice register-media-info --input-url "oss://<bucket>/<object>" --media-type video

Duration: ~3-5 seconds (async task)

Step 3: Translation Mode Confirmation (Phase 1) ⚠️ BLOCKING

Use AskUserQuestion to ask:

• "Do you need subtitle translation (translate subtitles only) or speech translation (translate subtitles + replace voiceover)?"

Must wait for user response!

Step 4: Subtitle Processing Confirmation (Phase 2) ⚠️ BLOCKING

Use AskUserQuestion to ask:

• "Do you need to erase original subtitles from the video?"
• "Do you need to burn-in translated subtitles?"

Must wait for user response!

Step 5: Output Path Confirmation (Phase 3)

• User specifies path → Use user's path
• User does not specify → Use default path and inform user

Default Path Rule: {source}_translated_{random8}.mp4

Step 6: Task Submission (Phase 5)

aliyun ice submit-video-translation-job \
  --input-config '{"Type":"Video","Video":"<mediaId>"}' \
  --output-config '{"MediaURL":"https://<output_url>"}' \
  --editing-config '{"TextSource":"OCR_ASR",...}'

Duration: ~2 seconds

Step 7: Task Polling (Phase 6)

Query every 30 seconds until task completes or fails.

Expected Duration:

• Subtitle-level translation: 3-5 minutes
• Speech-level translation: 10-20 minutes

Step 8: Result Retrieval (Phase 7)

• Get output video URL
• Generate signed URL (private Bucket)
• Output result to user

---

Scenario 2: Subtitle Review

Key: When user does not provide subtitle, MUST ask if subtitle extraction and review is needed!

Execution Flow

Phase 0 → Phase 1 → Phase 2 → 【MUST ASK】 Need subtitle review? →
User chooses review → Phase 4: Subtitle Review Confirmation → Phase 5 → Phase 6 → Phase 7

Detailed Steps

Step 1-5: Same as Scenario 1

Execute Phase 0-3, same flow.

Step 6: Need Subtitle Review? ⚠️ BLOCKING

Must Ask: When user does not provide subtitle, must confirm if extraction and review is needed!

Use AskUserQuestion to ask:

• "Do you need to extract subtitles for review first, or translate directly?"

Step 7: Subtitle Detection Region Confirmation ⚠️ BLOCKING

After user chooses review, ask subtitle detection region:

Use AskUserQuestion to ask:

• "Where are the subtitles roughly located in the video? Bottom 1/4, bottom 1/2?"

ROI Mapping Table:

Step 8: Subtitle Extraction (CaptionExtraction)

CLI Format Key: --Input, --Output, --JobParams must use JSON string format!

# Using MediaId (registered media)
aliyun ice SubmitIProductionJob \
  --FunctionName CaptionExtraction \
  --Input '{"Type":"MediaId","Media":"<mediaId>"}' \
  --Output '{"Type":"OSS","Media":"oss://<bucket>/<output>.srt"}' \
  --JobParams '{"lang":"ch","roi":[[0.5,1],[0,1]]}' \
  --force

# Or using OSS path
aliyun ice SubmitIProductionJob \
  --FunctionName CaptionExtraction \
  --Input '{"Type":"OSS","Media":"oss://<bucket>/<object>"}' \
  --Output '{"Type":"OSS","Media":"oss://<bucket>/<output>.srt"}' \
  --JobParams '{"lang":"ch","roi":[[0.5,1],[0,1]]}' \
  --force

Duration: 1-2 minutes

Step 9: Query Subtitle Extraction Result

Query every 30 seconds until Success or Fail.

Step 10: Subtitle Review Confirmation (Phase 4) ⚠️ BLOCKING

CRITICAL: Must execute strictly!

1. Get extracted subtitle content 2. Output subtitle content as-is to user (DO NOT change format) 3. AskUserQuestion: "Subtitle extraction complete, please check if content is correct, need modifications?" 4. Must wait for user confirmation

Step 11: Task Submission (Phase 5)

After user confirmation, submit translation task using reviewed SRT file:

aliyun ice submit-video-translation-job \
  --input-config '{"Type":"Video","Video":"<mediaId>","Subtitle":"<srt_https_url>"}' \
  --output-config '{"MediaURL":"https://<output_url>"}' \
  --editing-config '{"TextSource":"SubtitleFile",...}'

Step 12-13: Same as Scenario 1 Phase 6-7

---

Scenario 3: Subtitle Translation + User Subtitle

Execution Flow

Phase 0 → Phase 1 → Phase 2 → Phase 3 → Phase 5 → Phase 6 → Phase 7

Detailed Steps

Step 1-3: Same as Scenario 1

Execute Phase 0-2.

Step 4: Check Subtitle File

• Check user-provided SRT file OSS exists
• Validate SRT format (fix empty subtitle entries)

Step 5: Task Submission

aliyun ice submit-video-translation-job \
  --input-config '{"Type":"Video","Video":"<mediaId>","Subtitle":"<srt_https_url>"}' \
  --output-config '{"MediaURL":"https://<output_url>"}' \
  --editing-config '{"TextSource":"SubtitleFile","NeedSpeechTranslate":false,...}'

Key: NeedSpeechTranslate: false (subtitle translation mode)

---

Scenario 4: Speech Translation + User Subtitle

Execution Flow

Phase 0 → Phase 1 → Phase 2 → CustomSrtType Confirmation ⚠️ BLOCKING →
Phase 3 → Phase 5 → Phase 6 → Phase 7

Detailed Steps

Step 1-3: Same as Scenario 1

Execute Phase 0-2.

Step 4: CustomSrtType Confirmation ⚠️ BLOCKING

Must Ask: For speech translation + user subtitle, must confirm subtitle language type!

Use AskUserQuestion to ask:

• "Is the subtitle file you provided in source language or target language?"

Step 5: Task Submission

aliyun ice submit-video-translation-job \
  --input-config '{"Type":"Video","Video":"<mediaId>","Subtitle":"<srt_https_url>"}' \
  --output-config '{"MediaURL":"https://<output_url>"}' \
  --editing-config '{"TextSource":"SubtitleFile","NeedSpeechTranslate":true,"SpeechTranslate":{"CustomSrtType":"SourceSrt",...},...}'

Key: NeedSpeechTranslate: true + SpeechTranslate.CustomSrtType

---

Blocking Point Summary

---

Polling Strategy

Subtitle Extraction Task

• Interval: 30 seconds
• Timeout: 5 minutes
• States: Init → Queuing → Analysing → Processing → Success/Fail

Video Translation Task

• Interval: 30 seconds
• Timeout: 30 minutes
• States: Created → Executing → Finished/Failed

---

Time Estimation

---

End of Document