# Speech to Text — File Transcripts, Speaker Labels & Subtitles

> Speech to Text — File Transcripts, Speaker Labels & Subtitles is a paid MCP server for design and media. Transcribe audio and video URLs to text, with timings, subtitles and speaker labels. 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/hermeskd/audio-to-transcript
- **MCP Registry name:** io.github.kriton-dev/audio-to-transcript
- **Categories:** design and media, AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

This Apify Actor takes up to 20 media file URLs per run (MP3, M4A, WAV, FLAC, OGG, Opus, WebM, MP4, MOV, each up to 500 MB and 120 minutes) and returns one record per file. Language can be forced from 99 options or detected from the first speech, and output can include plain text with timed segments, SRT or WebVTT subtitles.

Optional extras: translation to English (the Actor calls it good for the gist of common European languages and rough for others), word-level timestamps for English and 24 other European languages, and anonymous speaker labels such as SPEAKER_1. Labels do not identify anyone, and they add a per-minute charge only when a speaker is found.

Billing is per started minute transcribed, and failed results are not charged. The previous schedule is $0.006 a minute, with $0.0075 requested from 2026-12-14, and the active Apify record decides the bill. Agents call it through Apify's MCP server and can cap spend with maxTotalChargeUsd.

## Features

- **File URL transcription:** Transcribes audio and video from http or https links.
- **Subtitle output:** Returns SRT or WebVTT alongside the text.
- **Speaker labels:** Marks who speaks when with anonymous labels.
- **Word timestamps:** Gives per-word timings for English and 24 other European languages.
- **Translate to English:** Returns an English version instead of the source language.
- **Spend cap:** A maximum charge stops work once reached.

## Good for

- Create subtitles for a video
- Transcribe a recorded meeting with speaker turns
- Translate foreign-language audio into rough English
- Let an agent transcribe files and pay per minute

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http audio-to-transcript 'https://mcp.apify.com/?tools=hermeskd/audio-to-transcript'
```

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

```sh
https://mcp.apify.com/?tools=hermeskd/audio-to-transcript
```

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

```json
{
  "mcpServers": {
    "audio-to-transcript": {
      "url": "https://mcp.apify.com/?tools=hermeskd/audio-to-transcript"
    }
  }
}
```

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

```json
{
  "servers": {
    "audio-to-transcript": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=hermeskd/audio-to-transcript"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "audio-to-transcript": {
      "serverUrl": "https://mcp.apify.com/?tools=hermeskd/audio-to-transcript"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "audio-to-transcript": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=hermeskd/audio-to-transcript"
    }
  }
}
```

## FAQ

### Which file types work?

MP3, M4A, WAV, FLAC, OGG, Opus, WebM, MP4 and MOV over http or https.

### How long can files be?

Up to 500 MB and 120 minutes each, with 1 to 20 files per run.

### Does speaker labelling identify people?

No. Speakers are anonymous and numbered in order of first speech.

### What does it cost?

$0.006 per audio minute on the previous schedule and $0.0075 on the requested one, plus $0.002 per speaker-labelled minute.

### Is Speech to Text — File Transcripts, Speaker Labels & Subtitles free?

No. Speech to Text — File Transcripts, Speaker Labels & Subtitles is a paid product.

### How do I add Speech to Text — File Transcripts, Speaker Labels & Subtitles to Claude Code?

Run this command in your terminal: claude mcp add --transport http audio-to-transcript 'https://mcp.apify.com/?tools=hermeskd/audio-to-transcript'

### What are the best alternatives to Speech to Text — File Transcripts, Speaker Labels & Subtitles?

The closest alternatives to Speech to Text — File Transcripts, Speaker Labels & Subtitles are HyperFrames by HeyGen, ffmpeg-skill, Claude Code Ultimate Guide, AvatarSay — Fictional Character & Talking Video MCP and ChartAnt.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [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.
- [AvatarSay — Fictional Character & Talking Video MCP](https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp): AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.
- [Hourlore](https://ai-powered.com/mcp/hourlore): Hourlore is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/speech-to-text-file-transcripts-speaker-labels-and-subtitles
