# speech-mcp

> speech-mcp — ng-bullseye-speech-mcp. Use this tool when you need to transcribe spoken language or generate synthetic speech, as it provides a unified interface for speech-to-text and text-to-speech functionality. It solves problems such as converting audio recordings to text or creating audio outputs from written text, using WhisperX transcription and Qwen3 TTS capabilities. It accepts audio files or text inputs and produces transcribed text or spoken audio outputs, making it ideal for applications requiring automated speech processing.

Canonical page: https://skillsregistry.net/skills/ng-bullseye-speech-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ng-bullseye-speech-mcp

## Description

Unified STT/TTS MCP server — WhisperX transcription + Qwen3 TTS, record/transcribe/speak tools.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/NG-Bullseye/speech-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ng-bullseye-speech-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ng-bullseye-speech-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ng-bullseye-speech-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt