Iflytek Video Translate logo

Iflytek Video Translate

Organization
iflytek
iflytek-video-translate

Use when user asks to translate videos, dub video content, or localize videos into other languages. Translate videos with AI-powered dubbing using iFlytek (Xfei) Video Translation API. Supports video language translation, voice dubbing, multilingual video localization, 视频翻译, 视频配音, 视频本地化. Features task creation, task list, task details retrieval. Ideal for content creators and localization teams.

Overview

Publisheriflytek
RepositoryiFly-Skills
Skill nameiflytek-video-translate
Stars
212
Forks
23
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by iflytek on GitHub. Read the source before you install it.

Installation

Install the Iflytek Video Translate AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/iflytek/iFly-Skills/tree/main/skills/iflytek-video-translate
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/iflytek/iFly-Skills.git /tmp/iFly-Skills
mkdir -p .claude/skills
cp -r /tmp/iFly-Skills/skills/iflytek-video-translate .claude/skills/iflytek-video-translate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Iflytek Video Translate in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Iflytek Video Translate on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Iflytek Video Translate is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Xfei Video Translation

Translate videos with AI-powered dubbing using iFlytek's Video Translation service.

API Endpoints

Base URL: https://spark-api-test.xf-yun.com/api/v1/video-translate

EndpointMethodDescription
/tasksPOSTCreate video translation task
/tasksGETList all tasks
/tasks/:taskIdGETGet task details

Features

  • Video Translation: Translate video audio to different languages
  • AI Dubbing: Generate natural-sounding voiceovers
  • Multi-language: Support for English, Chinese, Japanese, Korean, etc.
  • Task Management: Create tasks, list tasks, get task details
  • Lip Sync: Automatic face matching for translated audio

Usage Scenarios

Scenario 1: Create Video Translation Task

Submit a video for translation.

Use this when: User provides a video URL and wants to translate it.

bash
# Create task - translate English video to Chinese
python3 scripts/xfei_video_translate.py --action create_task \
    --file_url "https://example.com/video.mp4" \
    --src_lang en --dest_lang zh

# Translate Chinese to English
python3 scripts/xfei_video_translate.py --action create_task \
    --file_url "https://example.com/video.mp4" \
    --src_lang zh --dest_lang en

# Translate Japanese to Chinese
python3 scripts/xfei_video_translate.py --action create_task \
    --file_url "https://example.com/video.mp4" \
    --src_lang ja --dest_lang zh

Scenario 2: List All Tasks

View all video translation tasks.

Use this when: User wants to see all translation tasks.

bash
# List all tasks
python3 scripts/xfei_video_translate.py --action list_tasks

Scenario 3: Get Task Details

View detailed information about a specific task.

Use this when: User wants to check the status and details of a specific task.

bash
# Get task details
python3 scripts/xfei_video_translate.py --action get_task \
    --task_id "xxx-xxx-xxx"

Setup

1. Install Dependency

bash
pip install requests>=2.31.0

2. Configure Environment Variables

bash
export IFLY_API_KEY="your_api_key"
export IFLY_API_SECRET="your_api_secret"

兼容说明:设置任意 IFLY_* 凭证变量(包括空值)后,仅使用该组,缺项报错;未设置标准组时,依次尝试 XFYUN_*、XFEI_*,不跨组拼接。旧前缀会在 stderr 输出一次不含凭证值的迁移提示。

Parameters

create_task (POST /tasks)

ParameterTypeRequiredDescription
--file_url / -ustringYesVideo file OSS URL (视频文件 OSS 地址)
--src_lang / -fstringYesSource language code (e.g., en, zh, ja, ko)
--dest_lang / -tstringYesTarget language code

list_tasks (GET /tasks)

No parameters required.

get_task (GET /tasks/:taskId)

ParameterTypeRequiredDescription
--task_id / -istringYesTask ID

Response Format

Standard response: {"code": 0, "message": "success", "request_id": "xxx", "data": {}}

create_task Response (data)

json
{
  "task_id": "xxx-xxx-xxx",
  "status": "waiting_parsing",
  "created_at": "2025-01-17T10:30:45Z"
}

list_tasks Response (data)

json
[
  {
    "task_id": "xxx-xxx-xxx",
    "task_name": "我的翻译任务",
    "status": "completed",
    "src_lang": "en",
    "dest_lang": "zh",
    "created_at": "2025-01-17T10:30:45Z",
    "updated_at": "2025-01-17T11:30:45Z"
  }
]

get_task Response (data)

json
{
  "task_id": "xxx-xxx-xxx",
  "task_name": "我的翻译任务",
  "status": "completed",
  "created_at": "2025-01-17T10:30:45Z",
  "updated_at": "2025-01-17T11:30:45Z",
  "task_params": {
    "file_url": "https://example.com/video.mp4",
    "src_lang": "en",
    "dest_lang": "zh"
  },
  "output": {
    "subtitle_url": "https://example.com/output.srt",
    "output_video_url": "https://example.com/output.mp4"
  }
}

Task Status Values

StatusDescription
runningTask in progress
completedTask completed successfully
failedTask failed
cancelledTask cancelled
waiting_manual_intervention_segmentWaiting for transcript editing
waiting_manual_intervention_refineWaiting for translation editing

Language Codes

CodeLanguage
zhChinese (中文)
enEnglish (英文)
jaJapanese (日文)
koKorean (韩文)
ruRussian (俄文)
frFrench (法文)
arArabic (阿拉伯语)
esSpanish (西班牙语)
yueCantonese (粤语)

Input Video Requirements

  • Format: MP4
  • Duration: Max 5 minutes
  • Resolution: 720p - 4k
  • FPS: Recommended 25
  • Audio: Single audio track only

Error Handling

ErrorCauseSolution
IFLY_API_KEY and IFLY_API_SECRET are requiredNo credentials configuredSet environment variables
--file_url is requiredNo video URL providedProvide valid OSS video URL
--task_id is requiredNo task ID providedProvide valid task ID
API error XXXXRequest failedCheck message in response

鉴权失败错误提示 (๑•̀ㅂ•́)و✧

哎呀呀~遇到鉴权错误啦! (⊙_⊙) 快来看看是哪里出问题了吧~

HTTP Code错误描述原因处理建议
401{"message":"Unauthorized"}缺少 authorization 参数哎呀~检查一下有没有正确带上传入的 authorization 参数哦~
401{"message":"HMAC signature cannot be verified"}签名参数解析失败嗯嗯~ (°∀°)ノ 检查一下各签名参数是否完整,确认 APIKey 是不是正确呀~
401{"message":"HMAC signature does not match"}签名校验失败嘿呀~ (。•́︿•̀。) 检查一下 APIKey/APISecret 是否正确呢~还要看看 host、date、request-line 拼接对不对哦~signature 的 Base64 长度正常应该是 44 字节呢~
403{"message":"HMAC signature cannot be verified, a valid date or x-date header is required"}时钟偏移校验失败嗯嗯? (⊙_⊙) 服务器时钟可能有偏差哦~偏差超过 300 秒就会被拒绝啦!快去校准一下时间吧~

小贴士 💡:

  • 如果遇到签名不匹配的错误,首先检查 APIKey 和 APISecret 是否正确~
  • 确保服务器的日期时间准确,偏差太大会导致 403 错误哦~
  • 签名中的 path 需要和实际请求的路径完全一致才可以呢~

Tips

  1. Video URL: Must be an OSS (Aliyun Object Storage Service) URL accessible by iFlytek
  2. Task status: Use get_task to check task progress
  3. Completed tasks: When status is "completed", the output_video_url contains the translated video
  4. Manual intervention: Some videos may require human review for transcript or translation

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Iflytek Video Translate AI skill do?

Use when user asks to translate videos, dub video content, or localize videos into other languages. Translate videos with AI-powered dubbing using iFlytek (Xfei) Video Translation API. Supports video language translation, voice dubbing, multilingual video localization, 视频翻译, 视频配音, 视频本地化. Features task creation, task list, task details retrieval. Ideal for content creators and localization teams.

Why use Iflytek Video Translate on TypingMind?

Because you install it once and use it with any model. Iflytek Video Translate is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Iflytek Video Translate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/iflytek/iFly-Skills/tree/main/skills/iflytek-video-translate. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Iflytek Video Translate?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Iflytek Video Translate?

As many as you like. As long as a model supports skills, you can use Iflytek Video Translate with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Iflytek Video Translate AI skill free?

Yes. It is published on GitHub by iflytek under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇