eachlabs-tts

Transcribe audio from URL using EachLabs Speech-to-Text (Scribe v1).

7 stars

byDemerzels-lab

View on GitHub Installation ↓

Best use case

eachlabs-tts is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Transcribe audio from URL using EachLabs Speech-to-Text (Scribe v1).

Teams using eachlabs-tts should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/eachlabs-tts/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/fatih-developer/eachlabs-tts/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/eachlabs-tts/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How eachlabs-tts Compares

Feature / Agent	eachlabs-tts	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Transcribe audio from URL using EachLabs Speech-to-Text (Scribe v1).

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# EachLabs ElevenLabs Speech-to-Text

Transcribe audio files using EachLabs' integration with ElevenLabs Scribe v1 model. Supports diarization and timestamp granularity.

## Quick Start

```bash
# Basic transcription from URL
{baseDir}/scripts/transcribe.sh https://storage.googleapis.com/magicpoint/inputs/elevenlabs-s2t-input.mp3

# With speaker diarization
{baseDir}/scripts/transcribe.sh https://.../audio.mp3 --diarize

# Specify language (improves accuracy)
{baseDir}/scripts/transcribe.sh https://.../audio.mp3 --lang en

# Full JSON output with timestamps (word-level)
{baseDir}/scripts/transcribe.sh https://.../audio.mp3 --json
```

## Options

| Flag | Description |
|------|-------------|
| `--diarize` | Identify different speakers |
| `--lang CODE` | ISO language code (e.g., en, pt, es) |
| `--json` | Output full JSON with word timestamps |
| `--events` | Tag audio events (laughter, music, etc.) |

## Supported Input

Currently supports **Audio URLs** only. The file must be publicly accessible via HTTP/HTTPS.

## API Key

Set `EACHLABS_API_KEY` environment variable, or configure in clawdbot.json:

```json5
{
  skills: {
    entries: {
      "eachlabs-elevenlabs-stt": {
        apiKey: "el_..."
      }
    }
  }
}
```