# Wisprs

The Wisprs MCP server for Claude Code turns audio, video and public media links into transcripts. It can search the resulting text, translate it and create exportable files.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: Wisprs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Wisprs/wisprs-ai-connectors
- Updated: 2026-11-06
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/wisprs

## What it does

Wisprs sends public HTTPS media links to its hosted service for transcription. It can also search a transcript library and create translations, chapter lists, show notes or article drafts. The server runs remotely.

For local or private recordings, an authenticated Wisprs upload page handles the file; the model does not pass file contents or upload tokens. Transcripts can be exported as TXT, SRT, VTT, JSON, Markdown or DOCX. Access to the Wisprs service and browser-based OAuth are required. Transcription starts a billable asynchronous operation.

## Requirements
- Remote server: `https://wisprs.co/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http wisprs https://wisprs.co/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add wisprs --url https://wisprs.co/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "wisprs": {
            "url": "https://wisprs.co/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "wisprs": {
            "type": "http",
            "url": "https://wisprs.co/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http wisprs https://wisprs.co/api/mcp
```

## When to use it
- transcribe audio or video from a public link
- locate relevant moments in a transcript library
- translate a transcript and create chapter markers
- export transcript text as SRT or DOCX

## Example prompts
- Transcribe this video from its public link and create chapters.
- Find library moments where the project timeline is discussed.
- Translate this transcript and export it as SRT.

## Similar
- [Context7](https://affpapa.org/en/nevibecode/mcp/context7.md) — MCP server · 5563 installs
- [Search Google Flights](https://affpapa.org/en/nevibecode/mcp/search-google-flights.md) — MCP server · 2595 installs
- [Math-MCP](https://affpapa.org/en/nevibecode/mcp/math-mcp.md) — MCP server · 5958 installs
- [pipeworx gateway](https://affpapa.org/en/nevibecode/mcp/pipeworx-gateway.md) — MCP server · 419019 installs
- [SparkForge](https://affpapa.org/en/nevibecode/mcp/sparkforge.md) — MCP server · 219896 installs
- [OpenWebSearch](https://affpapa.org/en/nevibecode/mcp/openwebsearch.md) — MCP server · 494 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
