# Audio & Video to Text (SRT, VTT, RAG chunks)

> Audio & Video to Text (SRT, VTT, RAG chunks) is a paid MCP server for design and media. Turns audio and video files into timestamped text, SRT or VTT subtitles and citable chunks. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API, Web
- **Website:** https://apify.com/lif_manager/audio-video-transcription
- **Repository:** https://github.com/brunenjere/lif-tools
- **MCP Registry name:** io.github.BrunenJere/audio-video-transcription
- **Categories:** design and media, knowledge and memory, files and documents, AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

Chunk output is the part aimed at agents: segments are grouped to about 400 tokens by default, never cut mid-segment, overlap slightly, and keep start and end times so an answer can cite a minute mark such as 12:40. Each transcript also comes as Markdown and TXT files, and SRT or VTT subtitles use cues of at most two lines and about seven seconds.

Transcription uses open-source Whisper inside the Apify container, so audio is not sent to OpenAI or another API. An accurate mode uses Whisper small and a fast mode uses Whisper base, which is cheaper but makes more mistakes. Language is detected automatically across 90+ languages, with Spanish called out as a strength, and a vocabulary field helps spell names and terms.

It takes direct file URLs or an Apify storage you select, for formats from MP3 and M4A to MP4, MOV and MKV, up to 500 MB each. Links to YouTube, TikTok or Instagram are not supported. Pricing is pay per use through Apify, with an empty input running a free demo. The author notes it does not see your files unless you share run data.

## Features

- **Timestamped segments:** Every segment keeps its start and end time.
- **SRT and VTT output:** Subtitle cues of at most two lines and about seven seconds.
- **Citable RAG chunks:** Chunks keep whole segments, overlap slightly and carry time ranges.
- **Local Whisper:** Open-source Whisper runs inside the Apify container, with no third-party API.
- **Accuracy modes:** Whisper small for accuracy or Whisper base for a cheaper draft.
- **Vocabulary hints:** Add names and terms so they are spelled correctly.
- **Wide format support:** Handles MP3, WAV, M4A, OPUS, FLAC, MP4, MOV, MKV and more up to 500 MB.

## Good for

- Transcribe a recorded meeting and cite the minute of a decision
- Create subtitle files for a webinar
- Prepare podcast audio for a vector index
- Turn WhatsApp voice notes into text
- Transcribe classes or interviews in Spanish

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http audio-video-transcription 'https://mcp.apify.com/?tools=lif_manager/audio-video-transcription'
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.apify.com/?tools=lif_manager/audio-video-transcription
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "audio-video-transcription": {
      "url": "https://mcp.apify.com/?tools=lif_manager/audio-video-transcription"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "audio-video-transcription": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=lif_manager/audio-video-transcription"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "audio-video-transcription": {
      "serverUrl": "https://mcp.apify.com/?tools=lif_manager/audio-video-transcription"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "audio-video-transcription": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=lif_manager/audio-video-transcription"
    }
  }
}
```

## FAQ

### What does it cost?

Apify lists from $10 per 1,000 audio minutes (about $0.01 a minute), and the vendor README gives $0.004 a minute in fast mode.

### Is my audio sent to OpenAI?

No. The page says Whisper runs inside the Apify container with no third-party AI API.

### Can I transcribe a YouTube link?

No, links to video platforms are not supported; use direct links to files you own.

### What is the largest file?

500 MB per file.

### How do I call it from an agent?

Use the Apify API or MCP with a files list and an optional language, for example es.

### Is Audio & Video to Text (SRT, VTT, RAG chunks) free?

No. Audio & Video to Text (SRT, VTT, RAG chunks) is a paid product.

### How do I add Audio & Video to Text (SRT, VTT, RAG chunks) to Claude Code?

Run this command in your terminal: claude mcp add --transport http audio-video-transcription 'https://mcp.apify.com/?tools=lif_manager/audio-video-transcription'

### What are the best alternatives to Audio & Video to Text (SRT, VTT, RAG chunks)?

The closest alternatives to Audio & Video to Text (SRT, VTT, RAG chunks) are HyperFrames by HeyGen, Codebase Memory, XERJ, ffmpeg-skill and Claude Code Ultimate Guide.

## Where this comes from

- Description: written from the project's README and the project's website.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [NeuroStack](https://ai-powered.com/mcp/neurostack): NeuroStack is a freemium MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.

---
Source: https://ai-powered.com/mcp/audio-and-video-to-text-srt-vtt-rag-chunks
