一步API中文文档
    • 01_人工客服
    • 02_一步API福利群
    • 03_一步镜像站-福利群
    • 04_购买地址
    • 05_base_url说明
    • 06_API key的获取和使用
    • 07_支持的模型与在线查询
    • 08_API Key余额查询
    • 09 一镜视频平台操作指引(中文版)
    • 10 一镜视频平台操作指引(英文版)
    • 常用工具配置教程
      • 01 Chatbox 配置一步API
      • 02 PyCharm 配置一步API
      • 03 Cursor 配置一步API
      • 04 Trae AI 配置一步API
      • 05 CherryStudio 配置一步API
      • 06 Dify 配置一步API
      • 07 AingDesk 配置一步API
      • 08 VS Code 配置一步API
      • 09 IntelliJ IDEA 配置一步API
      • 10 immersivetranslate 沉浸式翻译配置一步API
      • 11 Zed 配置一步API
      • 12 DeepChat 配置一步API
      • 13 Void 配置一步API
      • 14 LibreChat 配置一步API
      • 15 Sider 配置一步API
      • 16 NextChat 配置一步API
      • 17 ChatWise 配置一步API
      • 18 Glarity 配置一步API
      • 19 Tavo 配置一步API
      • 20 OMate Chat 配置一步API
      • 21 Claude Code 配置一步API
      • 22 91写作配置
      • 23 OpenClaw自定义中转站配置教程
      • 24opencode配置一步API
      • 25Gemini CLI 配置一步API
      • 26CC switch配置一步API
      • Codex配置一步API
        • Windows
        • Mac
        • Linux
    • 聊天(Chat)
      • ChatGpt 接口
        • ChatGPT音频(Audio)
          • 创建视频
          • 音频转文字 whisper-1
          • 音频转文字 gpt-4o-transcribe
          • 创建语音 gpt-4o-mini-tts
          • 创建翻译 (不支持)
        • ChatGPT聊天(Chat)
          • 创建视频, 带图片
          • 连续修改生成视频
          • 获取令牌支持模型
          • 创建聊天识图 (流式)
          • 创建聊天识图 (流式) best64
          • 创建聊天识图 (非流)
          • 创建聊天创作图 (非流)
          • 官方Function calling调用
          • 官方N测试
          • 创建聊天函数调用
          • 创建结构化输出
          • 控制推理模型努力程度
          • 创建聊天补全 qwen-mt-turbo
          • 创建聊天补全 deepseek v3.1思考程度 (流式)
          • deepseek-ocr 识别
        • ChatGPT自动补全(Completions)
          • 创建完成
        • ChatGPT嵌入(Embeddings)
          • 创建嵌入
        • Web 搜索
          • web搜索
      • Anthropic Claude 接口
        • 创建聊天补全 (流式) [原生格式]
        • 创建函数调用 (流式) [原生格式]
        • 创建思考聊天 [原生格式]
        • 创建思考聊天
        • 创建聊天补全 (流式)
        • 创建聊天补全 (非流)
        • 创建聊天识图 (流式)
        • 创建聊天识图 (非流)
        • PDF支持 [原生格式]
        • PDF支持 [原生格式] base64格式
      • 谷歌Gemini 接口
        • 原生格式
          • 文本生成
          • 文本生成-流
          • 文本生成+思考-流
          • 图片生成
          • 图片生成 gemini-2.5-flash-image
          • 图片生成 gemini-2.5-flash-image 控制宽高比
          • 图片生成 gemini-3-pro-image-preview 控制宽高比 +清晰度
          • 图片编辑
          • 图片理解
          • 格式化输出
          • 函数调用
          • 文档理解
          • URL context [原生格式]
          • 代码执行
          • google search
          • 视频理解
          • URL context
          • 音频理解
          • Embeddings
    • 聊天(Responses)
      • 创建模型响应
      • 创建函数调用
      • 创建模型响应(流式返回)
      • 创建模型响应 (控制思考长度)
      • 创建网络搜索
      • 创建模型响应 gpt-5启用思考
    • 绘画模型
      • DALL·E 3
        • 创建 DALL·E 3
      • FLUX 系列
        • gpt 兼容格式
          • Flux 创建(OpenAI dall-e-3格式)
          • Flux编辑(OpenAI dall-e-3格式)
        • Replicate 官方格式
          • 创建任务 black-forest-labs/flux-kontext-dev
          • 查询任务
      • 豆包系列
        • doubao-seedream-4-0-250828-文生图
        • doubao-seedream-4-0-250828-图生图
        • doubao-seedream-4-0-250828-多图生图
      • gemini系列
        • gemini-3-pro-image-preview-单图编辑
        • gemini-3-pro-image-preview-文生图
    • 视频模型
      • veo 视频生成
        • OpenAI 视频格式
          • openai 创建视频,带图片
      • 万象视频生成
        • 创建视频 Copy
      • sora 视频生成
        • chat格式
          • 创建视频
          • 创建视频, 带图片
          • 连续修改生成视频
    • 音频(Audio)
      • TTS文本转语音
      • ASR语音转文本
    • 示例代码
      • python
        • 01 OpenAI-Python示例代码
        • 02 Claude-Python示例代码
        • 03 OpenAI-image-Python示例代码
        • 04 Gemini-Python示例代码
        • 05 Gemini多场景-Python代码示例
        • 06 Rerank-python示例代码
        • 07 Python分析文件代码示例
        • 08 whisper-1-Python实力代码
        • 09 dalle-3-Python示例代码
        • 10 doubao-Python示例代码
        • 11 gemini-image-Python示例代码
        • 12 gpt-image-1-Python示例代码
        • 13 sora-2-Python代码示例
        • 14_Pro/BAAI/bge-reranker-v2-m3-Python示例代码
        • 15 Gemini3 多轮工具调用示例
        • 16 Gemini image控制宽高比+清晰度代码示例
        • 17 Python其他示例
      • Java
        • 01 OpenAI-Java示例代码
        • 02 Claude-Java示例代码
        • 03 Gemini多场景-Java代码示例
    • 接口格式
      • Anthropic 对话格式(Messages)
      • Cohere 重排序格式(Rerank)
      • Deepseek reasoning 对话格式(类Chat Completions)
      • Jina AI 重排序格式(Rerank)
      • Midjourney 图像格式(Midjourney Proxy/Midjourney Proxy Plus)
      • OpenAI 音频格式
      • OpenAI 对话格式(Chat Completions)
      • OpenAI 嵌入格式(Embeddings)
      • OpenAI 图像格式(Image)
      • OpenAI 实时对话接口
      • OpenAI 响应格式(Responses)
      • Suno 音乐格式(Music)
      • Xinference 重排序格式(Rerank)
    • 搜索引擎
      • Google Serp Api

    10 一镜视频平台操作指引(英文版)

    Table of Contents#

    1. Platform Overview
    2. Registration & Login
    2.1 Email Registration
    2.2 Email Login
    2.3 Third-Party Login
    2.4 Forgot Password
    3. Home Page
    4. Create Video
    4.1 Configure API Key
    4.2 Describe Video Content
    4.3 Upload Materials
    4.4 Reference Materials
    4.5 Set Video Parameters
    4.6 Optimize Prompt
    4.7 Submit Generation
    5. Video Management
    5.1 Video List
    5.2 Search & Filter
    5.3 View Details
    5.4 Preview & Play
    5.5 Rename
    5.6 Download
    5.7 Share
    5.8 Delete
    6. Profile
    6.1 Personal Info
    6.2 Change Password
    6.3 API Key Management
    6.4 Usage Statistics
    7. System Settings
    7.1 Language Switching
    7.2 Theme Switching
    8. FAQ

    1. Platform Overview#

    TakeGen AI is an AI-powered video generation platform. Users can generate high-quality videos by entering text descriptions or uploading reference materials (images, audio, video).
    Core Features:
    AI-powered video generation (text-driven / image-driven)
    Multiple visual styles and aspect ratios
    Support for 480p / 720p / 1080p resolutions
    Customizable duration from 2 to 12 seconds
    AI auto dubbing and audio synthesis
    Video sharing

    2. Registration & Login#

    2.1 Email Registration#

    1.
    Open the platform and navigate to the registration page (click "Register Now" at the bottom of the login page).
    2.
    Enter your email address.
    3.
    Click "Send Code" — a 6-digit verification code will be sent to your email.
    4.
    Enter the verification code and set a password (minimum 6 characters).
    5.
    Phone number is optional.
    6.
    Click "Register" to complete. You will be automatically logged in and redirected to the home page.
    By registering, you agree to the platform's Terms of Service and Privacy Policy.

    2.2 Email Login#

    1.
    Open the login page.
    2.
    Enter the email and password you used during registration.
    3.
    Click "Login".

    2.3 Third-Party Login#

    The platform supports the following third-party login methods:
    GitHub Login: Click the "Login with GitHub" button on the login page. You will be redirected to GitHub for authorization, then automatically logged in.
    Google Login: Click the "Login with Google" button on the login page. You will be redirected to Google for authorization, then automatically logged in.

    2.4 Forgot Password#

    1.
    On the login page, click "Forgot Password?".
    2.
    Enter your registered email and click "Send Code".
    3.
    Enter the 6-digit verification code received in your email.
    4.
    Enter a new password (minimum 6 characters) and confirm it.
    5.
    Click "Reset Password". After a successful reset, you will be redirected to the login page.

    3. Home Page#

    After logging in, you will see the home page, which includes:
    Top Navigation Bar: Home / Create / Videos / Guide, along with language switching, theme switching, and user menu.
    Hero Section: Platform introduction with quick action buttons ("Start Creating" and "View Gallery").
    Feature Highlights: Showcases six core features — AI-Powered Generation, Image-Driven, Fast Processing, Multiple Styles, HD Output, and Audio Synthesis.
    How It Works: Describe Your Idea → AI Creates → Download & Share — three steps to create professional videos.
    Recent Videos: Displays up to 4 recently generated videos (if any). Click to navigate to the video management page.

    4. Create Video#

    Click "Create" in the navigation bar or the "Start Creating" button on the home page to enter the video creation page.

    4.1 Configure API Key#

    An API Key is required for first-time use:
    1.
    When entering the creation page without a configured API Key, a configuration dialog will appear.
    2.
    Enter your API Key (available from the API Key page).
    3.
    Click "Save". Once configured, you can start creating videos.
    You can also manage your API Key at any time from the "Profile" page.

    4.2 Describe Video Content#

    Enter a natural language description of the video you want in the input box. For example:
    "An orange cat sunbathing on a windowsill, sunlight streaming through the curtains"
    "City night scene, neon lights flickering, traffic flowing"
    "Waves crashing on the beach at sunset, the sky turning orange-red"
    Press Ctrl + Enter to send the message.

    4.3 Upload Materials#

    Three types of materials are supported:
    Material TypeSize LimitDescription
    ImageMax 10MBCan be used as a reference image or first frame
    AudioMax 20MBCan be used as background music or voiceover
    VideoMax 100MBCan be used as a reference video
    Click the upload button next to the input box and select the corresponding file type.

    4.4 Reference Materials#

    After uploading materials, use the @ symbol in the input box to reference them:
    1.
    Type @ in the input box — a material selection menu will appear.
    2.
    Click to select the material you want to reference.
    3.
    Example: "Use @Image1 as the first frame and generate a time-lapse video of a flower blooming"

    4.5 Set Video Parameters#

    The following video parameters can be adjusted on the creation page:
    ParameterOptionsDescription
    StyleMultiple optionsVisual style of the video
    Aspect Ratio16:9, 4:3, 1:1, 3:4, 9:16, 21:9Frame aspect ratio. "Smart Ratio" lets AI decide automatically
    Resolution480p, 720p, 1080pOutput resolution (1080p not available when using reference images)
    Duration2–12 secondsSet manually or choose "Smart Duration"
    AudioWith Audio / No AudioWhether to generate audio
    ModeReference / First & Last FrameGeneration mode when using image materials
    Click "Reset Parameters" to restore default settings.

    4.6 Optimize Prompt#

    After entering your description, click the "Optimize Prompt" button. AI will automatically refine your description to better suit video generation and improve output quality.

    4.7 Submit Generation#

    1.
    Confirm the video parameters are correct, then click "Confirm Generate".
    2.
    The system will submit the generation task, and you will receive a success notification.
    3.
    Check the generation progress on the "My Videos" page.
    4.
    You can continue describing new videos without waiting for the current one to finish.

    5. Video Management#

    Click "Videos" in the navigation bar to enter the video management page.

    5.1 Video List#

    Videos are displayed as cards, each containing:
    Thumbnail/Preview: Completed videos show a video preview; processing videos show a loading animation; failed ones show an error icon.
    Status Badge: Completed (green) / Processing (yellow) / Pending (gray) / Failed (red).
    Video Title: Defaults to the prompt content; can be customized.
    Parameter Tags: Style, ratio, resolution, duration, and other parameters.
    Action Buttons: Details, Rename, Download, Share, Delete.
    Pagination is supported with options for 5 / 10 / 20 / 50 items per page.

    5.2 Search & Filter#

    Keyword Search: Enter a keyword in the search box and press Enter or click "Search".
    Date Filter: Select a start date and end date to filter videos within a specific time range.
    Reset: Click "Reset" to clear all filters.

    5.3 View Details#

    Click the "Details" button on a video card to open a detail dialog, which includes:
    Basic Info: Task number, title, status, creation time, completion time.
    Video Parameters: Style, ratio, resolution, duration, audio settings.
    Prompt: The optimized or original prompt used for generation.
    Used Materials: Displays referenced images, audio, or video materials.

    5.4 Preview & Play#

    Click the thumbnail of a completed video to open a full-screen player for preview.

    5.5 Rename#

    1.
    Click the "Rename" button on a video card.
    2.
    Edit the title in the popup (maximum 100 characters).
    3.
    Click "Save" to apply.

    5.6 Download#

    Click the "Download" button on a completed video. The system will open a download link to save the video locally.

    5.7 Share#

    1.
    Click the "Share" button on a completed video.
    2.
    The system automatically generates a share link and copies it to the clipboard.
    3.
    Send the link to others — they can view the video without logging in.
    The share page displays a video player, the prompt description, and view count.

    5.8 Delete#

    1.
    Click the "Delete" button on a video card.
    2.
    Confirm the deletion in the popup dialog.
    3.
    The video will be permanently deleted and cannot be recovered.

    6. Profile#

    Click your avatar in the top-right corner and select "Profile" to enter.

    6.1 Personal Info#

    Email: Displays your registered email (read-only).
    Phone: Add or update your phone number, then click "Save".

    6.2 Change Password#

    If you already have a password: Enter current password + new password + confirm new password.
    If you registered via third-party login (no password set): Enter new password + confirm new password only.
    New password must be at least 6 characters.

    6.3 API Key Management#

    View Status: Shows "Configured" or "Not Configured".
    Save API Key: Enter your API Key and click "Save API Key".
    Clear API Key: Click "Clear API Key" to revert to the system default key.
    Get API Key: Click the "Get API Key" link to navigate to the API Key page.
    After configuring a custom API Key, the platform will use your own key for AI services. If left empty, the system default key is used.

    6.4 Usage Statistics#

    Used Today: Number of videos generated today.
    Total Used: Total number of videos generated.

    7. System Settings#

    7.1 Language Switching#

    Click the language toggle button (globe icon) on the right side of the top navigation bar to switch between Chinese and English.
    All interface text updates in real time after switching.
    The browser tab title also changes accordingly (Chinese: 一镜AI / English: TakeGen AI).
    Language preference is saved locally and applied automatically on your next visit.

    7.2 Theme Switching#

    Click the theme toggle button (moon/sun icon) on the right side of the top navigation bar to switch between dark and light themes.
    Dark Theme: Dark background, suitable for nighttime use.
    Light Theme: White background, suitable for daytime use.
    Theme preference is saved locally and applied automatically on your next visit.

    8. FAQ#

    Q: How long does video generation take?
    A: Generation time depends on the video duration, resolution, and other parameters. You can continue using other features while waiting. The status will update automatically once generation is complete.
    Q: Why does it say "1080p not supported"?
    A: 1080p resolution is not supported when using reference images. The system will automatically downgrade to 720p. Pure text-to-video generation is not affected by this limitation.
    Q: What should I do if video generation fails?
    A: Check the failure reason on the "My Videos" page (click "Details" to view the error message). Modify your prompt or parameters and try again.
    Q: How long are shared video links valid?
    A: Share links are permanent. Anyone can view the video through the link without logging in.
    Q: How do I get an API Key?
    A: Visit the API Key page and follow the instructions to apply. Once obtained, configure it in "Profile" or on the creation page.
    Q: What aspect ratios are supported?
    A: 16:9 (landscape), 4:3 (traditional), 1:1 (square), 3:4 (portrait), 9:16 (mobile portrait), 21:9 (ultrawide), and "Smart Ratio" where AI selects automatically.
    Q: Can I generate multiple videos at the same time?
    A: Yes. After submitting one generation task, you can immediately describe and submit another video. The system queues tasks and processes them sequentially.
    修改于 2026-02-23 08:13:40
    上一页
    09 一镜视频平台操作指引(中文版)
    下一页
    01 Chatbox 配置一步API
    Built with