Stt

Name: Stt
Author: sebderhy

ASecurity

Transcribe audio files to text. Supports mp3, wav, m4a, ogg, webm, mp4, flac. Returns accurate transcription with language detection.

6 stars
0 votes
0 copies
3 views
Added September 2, 2026

ai-agentsshellbashapi

Works with

Security analysis

A100/100

Scanned September 2, 2026

npx -y skills add sebderhy/shellteam --skill stt --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Stt?

Add the live security badge to your README. It updates with every re-scan.

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sebderhy-stt/badge)](https://www.skillsdirectory.com/skills/sebderhy-stt)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
name: stt
description: Transcribe audio files to text. Supports mp3, wav, m4a, ogg, webm, mp4, flac. Returns accurate transcription with language detection.
---

Transcribe an audio file to text.

## Steps

1. Upload the audio file to the proxy endpoint:

```bash
curl -s -X POST {api_base}/internal/ai/stt \
  -H "Authorization: Bearer $SHELLTEAM_AI_TOKEN" \
  -H "X-Shellteam-User-Id: $SHELLTEAM_USER_ID" \
  -F "file=@/path/to/audio.mp3"
```

2. The response is JSON: `{"text": "transcribed text here", "language_code": "en"}`

3. Display the transcript text to the user.

## Supported Formats

mp3, wav, m4a, ogg, webm, mp4, flac