Subtitle Generator MCP Server

Generate SRT/VTT subtitles from audio and video files, translate subtitles to any language using local AI models. No external API calls — 100% privacy.

Features

Tool	Description	Price
generate_subtitle	Generate subtitles (SRT/VTT/TXT) from audio/video using Whisper AI	$0.10/use
translate_subtitle	Translate subtitle content to any language, preserving timestamps	$0.08/use

Connect via Claude Desktop

Add to your Claude Desktop MCP settings:

{
  "mcpServers": {
    "subtitle-generator": {
      "url": "https://ntriqpro--subtitle-generator-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
    }
  }
}

Supported Audio/Video Formats

MP3, WAV, M4A, MP4, OGG, FLAC, WebM, and other common audio/video formats.

Input

generate_subtitle

• audioUrl (required): URL of audio or video file to process
• format (optional): Output format — "srt" (default), "vtt", or "txt"
• language (optional): Audio language code (e.g., "en", "ko", "ja") for better accuracy. Auto-detect if omitted.

translate_subtitle

• subtitleContent (required): SRT or VTT subtitle content to translate
• targetLanguage (required): Target language code (e.g., "ko", "ja", "zh", "es", "fr", "de")

Output Examples

generate_subtitle

{
  "status": "success",
  "subtitle_content": "1\n00:00:00,000 --> 00:00:03,500\nHello, welcome to today's meeting.\n\n2\n00:00:03,500 --> 00:00:07,200\nLet's start with the agenda.",
  "format": "srt",
  "segments_count": 15,
  "detected_language": "en",
  "model": "whisper-large-v3-turbo"
}

translate_subtitle

{
  "status": "success",
  "subtitle_content": "1\n00:00:00,000 --> 00:00:03,500\n안녕하세요, 오늘 회의에 오신 것을 환영합니다.\n\n2\n00:00:03,500 --> 00:00:07,200\n의제부터 시작하겠습니다.",
  "target_language": "ko",
  "segments_translated": 15,
  "model": "qwen-3.5"
}

Technology

• Speech Recognition: OpenAI Whisper (MIT License)
• Translation: Qwen 3.5 (Apache 2.0 License)
• Processing: Local AI inference, zero external API calls
• Privacy: Audio/video files are processed in real-time and not stored

Open Source Licenses

This service uses the following open source models:

• OpenAI Whisper — MIT License
• Qwen 3.5 — Apache 2.0 License

Legal Disclaimer

Audio Data Privacy Notice: Users are solely responsible for ensuring they have obtained all necessary consents and authorizations before submitting audio or video recordings for processing. Audio/video data is processed in real-time and is not stored, retained, or used for model training. This service is provided as a tool for subtitle generation and does not constitute legal advice regarding recording or privacy compliance.

Platform usage is free. You only pay per event (see pricing above).