# SiliconFlow Voice Transcription

> Use this tool when you need to transcribe audio files into text with high accuracy, solving problems such as voice-to-text conversion, speech recognition, and audio data analysis. It takes in base64-encoded audio input or uploaded audio files and outputs transcription results with confidence scores. Ideal for AI workflows, virtual assistants, and applications requiring automated speech recognition.

Canonical page: https://skillsregistry.net/skills/aio-2030-siliconflow-voice-transcription  
JSON: https://api.skillsregistry.net/v1/skills/aio-2030-siliconflow-voice-transcription

## Description

MCP-Audio is a Flask-based server that provides voice transcription capabilities by integrating with SiliconFlow's audio processing API. The server exposes endpoints for audio file uploads, processes them using the FunAudioLLM/SenseVoiceSmall model, and returns transcription results with confidence scores. It includes Docker containerization with ffmpeg support, handles base64-encoded audio input, and implements proper error handling and file management, making it suitable for applications requiring voice-to-text conversion in AI workflows.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/aio-2030-siliconflow-voice-transcription)
- **Repository:** <https://github.com/aio-2030/mcp-audio>

## 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": "aio-2030-siliconflow-voice-transcription"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/aio-2030-siliconflow-voice-transcription` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/aio-2030-siliconflow-voice-transcription/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