subtitle-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Subtitle Generation

字幕生成

Generate professional subtitles and captions for videos using each::sense. This skill creates accurate transcriptions, multi-language subtitles, animated captions, and various export formats optimized for social media, video production, and accessibility.

使用each::sense为视频生成专业级字幕和字幕文件。该功能可生成精准的转录文本、多语言字幕、动画字幕，以及针对社交媒体、视频制作和无障碍场景优化的多种导出格式。

Features

功能特性

Auto-Generated Subtitles: Automatic speech-to-text transcription with accurate timing
Multi-Language Generation: Generate subtitles in multiple languages from audio
Animated Captions: TikTok/Instagram-style animated word-by-word captions
SRT/VTT Export: Standard subtitle formats for editing and distribution
Speaker Diarization: Identify and label different speakers in conversations
Subtitle Translation: Translate existing subtitles to other languages
Burned-In Subtitles: Render subtitles directly into video (hardcoded)
Karaoke Style: Word-by-word highlighting for music and lyric videos
Timing Adjustment: Fine-tune subtitle timing and synchronization
Batch Processing: Generate subtitles for multiple videos at once

自动生成字幕：带精准时间轴的自动语音转文本转录
多语言生成：从音频生成多种语言的字幕
动画字幕：TikTok/Instagram风格的逐词动画字幕
SRT/VTT导出：用于编辑和分发的标准字幕格式
说话人分离：识别并标记对话中的不同说话人
字幕翻译：将现有字幕翻译为其他语言
内嵌式字幕：将字幕直接渲染到视频中（硬编码）
卡拉OK风格：针对音乐和歌词视频的逐词高亮显示
时间轴调整：微调字幕的时间轴和同步性
批量处理：一次性为多个视频生成字幕

Quick Start

快速开始

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video with accurate timestamps",
    "mode": "max",
    "file_urls": ["https://example.com/my-video.mp4"]
  }'

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Generate subtitles for this video with accurate timestamps",
    "mode": "max",
    "file_urls": ["https://example.com/my-video.mp4"]
  }'

Subtitle Formats & Outputs

字幕格式与输出

Format	Extension	Use Case
SRT	.srt	Universal, most video players and editors
VTT	.vtt	Web video, HTML5 players, YouTube
Burned-In	.mp4	Social media, no player support needed
JSON	.json	Custom applications, programmatic access
ASS/SSA	.ass	Advanced styling, anime subtitles

格式	扩展名	适用场景
SRT	.srt	通用格式，支持大多数视频播放器和编辑器
VTT	.vtt	网页视频、HTML5播放器、YouTube
内嵌式	.mp4	社交媒体，无需播放器支持
JSON	.json	Custom applications, programmatic access
ASS/SSA	.ass	高级样式、动漫字幕

Use Case Examples

使用场景示例

1. Auto-Generate Subtitles from Video

1. 从视频自动生成字幕

Automatically transcribe speech from a video file with accurate word-level timestamps.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transcribe this video and generate subtitles with accurate timestamps. Output as SRT format. The video contains English speech.",
    "mode": "max",
    "file_urls": ["https://example.com/interview-video.mp4"]
  }'

自动转录视频文件中的语音，并生成带精准逐词时间轴的字幕。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Transcribe this video and generate subtitles with accurate timestamps. Output as SRT format. The video contains English speech.",
    "mode": "max",
    "file_urls": ["https://example.com/interview-video.mp4"]
  }'

2. Multi-Language Subtitle Generation

2. 多语言字幕生成

Generate subtitles in multiple languages directly from the audio.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video in English, Spanish, and French. Provide separate SRT files for each language. The original audio is in English.",
    "mode": "max",
    "file_urls": ["https://example.com/product-demo.mp4"]
  }'

直接从音频生成多种语言的字幕。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Generate subtitles for this video in English, Spanish, and French. Provide separate SRT files for each language. The original audio is in English.",
    "mode": "max",
    "file_urls": ["https://example.com/product-demo.mp4"]
  }'

3. Animated/Styled Captions (TikTok Style)

3. 动画/样式化字幕（TikTok风格）

Create eye-catching animated captions with word-by-word highlighting, popular on TikTok and Instagram Reels.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Add TikTok-style animated captions to this video. Use bold white text with black outline, word-by-word pop animation, centered at the bottom third of the screen. Make it trendy and engaging.",
    "mode": "max",
    "file_urls": ["https://example.com/short-form-content.mp4"]
  }'

创建引人注目的逐词高亮动画字幕，在TikTok和Instagram Reels上广受欢迎。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Add TikTok-style animated captions to this video. Use bold white text with black outline, word-by-word pop animation, centered at the bottom third of the screen. Make it trendy and engaging.",
    "mode": "max",
    "file_urls": ["https://example.com/short-form-content.mp4"]
  }'

4. SRT/VTT Export

4. SRT/VTT导出

Generate clean subtitle files in standard formats for use in video editors or streaming platforms.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transcribe this video and export subtitles in both SRT and VTT formats. Ensure proper line breaks (max 42 characters per line, 2 lines max). Include timestamps accurate to milliseconds.",
    "mode": "max",
    "file_urls": ["https://example.com/documentary.mp4"]
  }'

生成标准格式的清晰字幕文件，用于视频编辑器或流媒体平台。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Transcribe this video and export subtitles in both SRT and VTT formats. Ensure proper line breaks (max 42 characters per line, 2 lines max). Include timestamps accurate to milliseconds.",
    "mode": "max",
    "file_urls": ["https://example.com/documentary.mp4"]
  }'

5. Speaker Diarization (Identify Speakers)

5. 说话人分离（识别说话人）

Generate subtitles that identify and label different speakers in conversations, interviews, or podcasts.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this podcast with speaker diarization. There are 2 speakers - identify them as Speaker 1 and Speaker 2 (or Host and Guest if you can determine roles). Format each line with the speaker label.",
    "mode": "max",
    "file_urls": ["https://example.com/podcast-episode.mp4"]
  }'

生成可识别并标记对话、访谈或播客中不同说话人的字幕。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Generate subtitles for this podcast with speaker diarization. There are speakers - identify them as Speaker 1 and Speaker 2 (or Host and Guest if you can determine roles). Format each line with the speaker label.",
    "mode": "max",
    "file_urls": ["https://example.com/podcast-episode.mp4"]
  }'

6. Subtitle Translation

6. 字幕翻译

Translate existing subtitles from one language to another while preserving timing.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Translate these English subtitles to Japanese. Preserve the original timing and format. Ensure natural Japanese phrasing rather than literal translation.",
    "mode": "max",
    "file_urls": ["https://example.com/original-subtitles.srt"]
  }'

在保留时间轴的前提下，将现有字幕从一种语言翻译为另一种语言。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Translate these English subtitles to Japanese. Preserve the original timing and format. Ensure natural Japanese phrasing rather than literal translation.",
    "mode": "max",
    "file_urls": ["https://example.com/original-subtitles.srt"]
  }'

7. Burned-In Subtitles

7. 内嵌式字幕

Render subtitles directly into the video file (hardcoded/embedded) so they appear without needing player support.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate subtitles for this video and burn them directly into the video. Use white text with black background box, Arial font, positioned at bottom center. Output a new video file with embedded subtitles.",
    "mode": "max",
    "file_urls": ["https://example.com/social-media-clip.mp4"]
  }'

将字幕直接渲染到视频文件中（硬编码/内嵌），无需播放器支持即可显示。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Generate subtitles for this video and burn them directly into the video. Use white text with black background box, Arial font, positioned at bottom center. Output a new video file with embedded subtitles.",
    "mode": "max",
    "file_urls": ["https://example.com/social-media-clip.mp4"]
  }'

8. Word-by-Word Karaoke Style

8. 逐词卡拉OK风格

Create karaoke-style subtitles with word-by-word highlighting, perfect for music videos and lyric content.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Create karaoke-style subtitles for this music video. Display lyrics with word-by-word highlighting as they are sung. Use a gradient color change effect (from white to yellow) for the currently sung word. Center the text on screen.",
    "mode": "max",
    "file_urls": ["https://example.com/music-video.mp4"]
  }'

创建带逐词高亮的卡拉OK风格字幕，非常适合音乐视频和歌词内容。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Create karaoke-style subtitles for this music video. Display lyrics with word-by-word highlighting as they are sung. Use a gradient color change effect (from white to yellow) for the currently sung word. Center the text on screen.",
    "mode": "max",
    "file_urls": ["https://example.com/music-video.mp4"]
  }'

9. Subtitle Timing Adjustment

9. 字幕时间轴调整

Fine-tune subtitle timing for better synchronization with audio.

bash

undefined

微调字幕时间轴，实现与音频的更好同步。

bash

undefined

First, upload video and generate initial subtitles

curl -X POST https://sense.eachlabs.run/chat
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-H "Accept: text/event-stream"
-d '{ "message": "Generate subtitles for this video", "mode": "max", "session_id": "subtitle-timing-project", "file_urls": ["https://example.com/video-with-delay.mp4"] }'

curl -X POST https://sense.eachlabs.run/chat \ -H "Content-Type: application/json" \ -H "X-API-Key: $EACHLABS_API_KEY" \ -H "Accept: text/event-stream" \ -d '{ "message": "Generate subtitles for this video", "mode": "max", "session_id": "subtitle-timing-project", "file_urls": ["https://example.com/video-with-delay.mp4"] }'

Then adjust timing in the same session

curl -X POST https://sense.eachlabs.run/chat
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-H "Accept: text/event-stream"
-d '{ "message": "The subtitles are appearing 500 milliseconds too early. Shift all subtitle timings forward by 500ms and regenerate the SRT file.", "session_id": "subtitle-timing-project" }'

undefined

curl -X POST https://sense.eachlabs.run/chat \ -H "Content-Type: application/json" \ -H "X-API-Key: $EACHLABS_API_KEY" \ -H "Accept: text/event-stream" \ -d '{ "message": "The subtitles are appearing 500 milliseconds too early. Shift all subtitle timings forward by 500ms and regenerate the SRT file.", "session_id": "subtitle-timing-project" }'

undefined

10. Batch Subtitle Generation

10. 批量字幕生成

Generate subtitles for multiple videos in a single workflow.

bash

curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Generate English subtitles for all these videos. Output SRT files for each. Use consistent formatting across all videos: max 2 lines, 42 characters per line, minimum 1 second display time per subtitle.",
    "mode": "max",
    "file_urls": [
      "https://example.com/episode-01.mp4",
      "https://example.com/episode-02.mp4",
      "https://example.com/episode-03.mp4"
    ]
  }'

在单个工作流中为多个视频生成字幕。

bash

curl -X POST https://sense.eachlabs.run/chat \\
  -H "Content-Type: application/json" \\
  -H "X-API-Key: $EACHLABS_API_KEY" \\
  -H "Accept: text/event-stream" \\
  -d '{
    "message": "Generate English subtitles for all these videos. Output SRT files for each. Use consistent formatting across all videos: max 2 lines, 42 characters per line, minimum 1 second display time per subtitle.",
    "mode": "max",
    "file_urls": [
      "https://example.com/episode-01.mp4",
      "https://example.com/episode-02.mp4",
      "https://example.com/episode-03.mp4"
    ]
  }'

Best Practices

最佳实践

Transcription Quality

转录质量

Clear Audio: Best results with clear speech and minimal background noise
Language Hint: Specify the source language for better accuracy
Speaker Count: Mention number of speakers for better diarization
Context: Provide context about the content (technical terms, names) for accuracy

清晰音频：语音清晰、背景噪音最小的音频效果最佳
语言提示：指定源语言可提高准确性
说话人数量：说明说话人数量可优化分离效果
上下文：提供内容上下文（专业术语、名称）以提升准确性

Subtitle Formatting

字幕格式

Line Length: Keep lines under 42 characters for readability
Duration: Each subtitle should display for 1-7 seconds
Lines Per Subtitle: Maximum 2 lines per subtitle block
Reading Speed: Target 150-180 words per minute for comfortable reading

行长度：每行不超过42个字符，确保可读性
显示时长：每个字幕块显示1-7秒
每行字幕数：每个字幕块最多2行
阅读速度：目标为每分钟150-180词，保证舒适阅读

Animated Captions

动画字幕

Font Choice: Bold, sans-serif fonts work best for short-form content
Contrast: Use outlines or shadows for visibility on any background
Position: Keep safe zones clear for platform UI elements
Animation: Subtle animations are more readable than dramatic effects

字体选择：粗体无衬线字体最适合短视频内容
对比度：使用描边或阴影确保在任何背景下都可见
位置：避开平台UI元素的安全区域
动画效果：微妙的动画比夸张效果更易读

Translation

翻译

Cultural Adaptation: Request localization, not just translation
Timing Flexibility: Some languages need more time to read
Character Limits: CJK languages often need fewer characters per line

文化适配：请求本地化而非单纯翻译
时间轴灵活性：部分语言需要更长的阅读时间
字符限制：中日韩语言通常每行需要更少字符

Prompt Tips for Subtitle Generation

字幕生成提示词技巧

When requesting subtitles, include these details in your prompt:

Source Language: What language is spoken in the video?
Target Format: SRT, VTT, burned-in, or animated?
Style Requirements: Font, color, position, animation
Speaker Info: Number of speakers, roles if known
Special Terms: Technical vocabulary, names, brands
Output Languages: Single language or multiple translations

请求字幕时，请在提示词中包含以下细节：

源语言：视频中使用的是哪种语言？
目标格式：SRT、VTT、内嵌式还是动画字幕？
样式要求：字体、颜色、位置、动画效果
说话人信息：说话人数量，已知的角色
特殊术语：专业词汇、名称、品牌
输出语言：单一语言还是多种翻译版本

Example Prompt Structure

提示词结构示例

"Generate [format] subtitles for this video.
Source language: [language].
[Number] speakers: [roles if known].
Style: [font, color, position requirements].
Special terms to recognize: [names, technical words].
Additional requirements: [line length, timing, etc.]"

"Generate [format] subtitles for this video.
Source language: [language].
[Number] speakers: [roles if known].
Style: [font, color, position requirements].
Special terms to recognize: [names, technical words].
Additional requirements: [line length, timing, etc.]"

Mode Selection

模式选择

Ask your users before generating:

"Do you want fast & cheap, or high quality?"

Mode	Best For	Speed	Quality
`max`	Final subtitles, professional content, accuracy-critical	Slower	Highest
`eco`	Quick drafts, review copies, bulk processing	Faster	Good

生成前请询问用户：

"您需要快速低成本的版本，还是高质量版本？"

模式	最佳适用场景	速度	质量
`max`	最终字幕、专业内容、对准确性要求高的场景	较慢	最高
`eco`	快速草稿、审阅副本、批量处理	较快	良好

Multi-Turn Subtitle Refinement

多轮字幕优化

Use

session_id

to iterate on subtitle generation:

bash

undefined

使用

session_id

迭代优化字幕生成：

bash

undefined

Initial subtitle generation

curl -X POST https://sense.eachlabs.run/chat
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-H "Accept: text/event-stream"
-d '{ "message": "Generate subtitles for this video with speaker identification", "session_id": "subtitle-project-001", "file_urls": ["https://example.com/interview.mp4"] }'

curl -X POST https://sense.eachlabs.run/chat \ -H "Content-Type: application/json" \ -H "X-API-Key: $EACHLABS_API_KEY" \ -H "Accept: text/event-stream" \ -d '{ "message": "Generate subtitles for this video with speaker identification", "session_id": "subtitle-project-001", "file_urls": ["https://example.com/interview.mp4"] }'

Refine based on feedback

curl -X POST https://sense.eachlabs.run/chat
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-H "Accept: text/event-stream"
-d '{ "message": "Change Speaker 1 label to John and Speaker 2 to Sarah. Also fix the spelling of TensorFlow wherever it appears.", "session_id": "subtitle-project-001" }'

curl -X POST https://sense.eachlabs.run/chat \ -H "Content-Type: application/json" \ -H "X-API-Key: $EACHLABS_API_KEY" \ -H "Accept: text/event-stream" \ -d '{ "message": "Change Speaker 1 label to John and Speaker 2 to Sarah. Also fix the spelling of TensorFlow wherever it appears.", "session_id": "subtitle-project-001" }'

Add styling and export

curl -X POST https://sense.eachlabs.run/chat
-H "Content-Type: application/json"
-H "X-API-Key: $EACHLABS_API_KEY"
-H "Accept: text/event-stream"
-d '{ "message": "Now create a burned-in version with the corrected subtitles. Use yellow text for John and cyan for Sarah.", "session_id": "subtitle-project-001" }'

undefined

curl -X POST https://sense.eachlabs.run/chat \ -H "Content-Type: application/json" \ -H "X-API-Key: $EACHLABS_API_KEY" \ -H "Accept: text/event-stream" \ -d '{ "message": "Now create a burned-in version with the corrected subtitles. Use yellow text for John and cyan for Sarah.", "session_id": "subtitle-project-001" }'

undefined

Language Support

语言支持

each::sense supports subtitle generation in 50+ languages including:

Language	Code	Notes
English	en	US, UK, AU variants
Spanish	es	Latin American and European
French	fr	France and Canadian
German	de
Japanese	ja
Korean	ko
Chinese	zh	Simplified and Traditional
Arabic	ar	RTL support
Hindi	hi
Portuguese	pt	Brazilian and European

each::sense支持50多种语言的字幕生成，包括：

语言	代码	说明
英语	en	支持美国、英国、澳大利亚变体
西班牙语	es	支持拉美和欧洲变体
法语	fr	支持法国和加拿大变体
德语	de
日语	ja
韩语	ko
中文	zh	支持简体和繁体
阿拉伯语	ar	支持从右到左显示
印地语	hi
葡萄牙语	pt	支持巴西和欧洲变体

Error Handling

错误处理

Error	Cause	Solution
`Failed to create prediction: HTTP 422`	Insufficient balance	Top up at eachlabs.ai
Transcription quality low	Poor audio quality	Provide cleaner audio source
Language detection failed	Mixed languages or unclear speech	Specify source language explicitly
Timeout	Long video or complex processing	Set client timeout to minimum 10 minutes

错误	原因	解决方案
`Failed to create prediction: HTTP 422`	余额不足	在eachlabs.ai充值
转录质量低	音频质量差	提供更清晰的音频源
语言检测失败	混合语言或语音不清晰	明确指定源语言
超时	视频过长或处理复杂	将客户端超时设置为至少10分钟

Client Configuration

客户端配置

Important: Subtitle generation can take significant time for long videos.

Minimum timeout: 10 minutes (600 seconds)
Recommended: Set timeout based on video length (2-3 minutes per minute of video)
Streaming: Use SSE event handling to show progress

重要提示：长视频的字幕生成可能需要较长时间。

最小超时时间：10分钟（600秒）
推荐设置：根据视频长度设置超时（每1分钟视频对应2-3分钟超时）
流式处理：使用SSE事件处理显示进度

subtitle-generation

Original

Translation

Subtitle Generation

字幕生成

Features

功能特性

Quick Start

快速开始

Subtitle Formats & Outputs

字幕格式与输出

Use Case Examples

使用场景示例

1. Auto-Generate Subtitles from Video

1. 从视频自动生成字幕

2. Multi-Language Subtitle Generation

2. 多语言字幕生成

3. Animated/Styled Captions (TikTok Style)

3. 动画/样式化字幕（TikTok风格）

4. SRT/VTT Export

4. SRT/VTT导出

5. Speaker Diarization (Identify Speakers)

5. 说话人分离（识别说话人）

6. Subtitle Translation

6. 字幕翻译

7. Burned-In Subtitles

7. 内嵌式字幕

8. Word-by-Word Karaoke Style

8. 逐词卡拉OK风格

9. Subtitle Timing Adjustment

9. 字幕时间轴调整

First, upload video and generate initial subtitles

First, upload video and generate initial subtitles

Then adjust timing in the same session

Then adjust timing in the same session

10. Batch Subtitle Generation

10. 批量字幕生成

Best Practices

最佳实践

Transcription Quality

转录质量

Subtitle Formatting

字幕格式

Animated Captions

动画字幕

Translation

翻译

Prompt Tips for Subtitle Generation

字幕生成提示词技巧

Example Prompt Structure

提示词结构示例

Mode Selection

模式选择

Multi-Turn Subtitle Refinement

多轮字幕优化

Initial subtitle generation

Initial subtitle generation

Refine based on feedback

Refine based on feedback

Add styling and export

Add styling and export

Language Support

语言支持

Error Handling

错误处理

Client Configuration

客户端配置

Related Skills

相关功能