Installation

$ npx skills add krishagel/geoffrey --skill elevenlabs-tts

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared

Cursor Not declared

Codex Not declared

GitHub Copilot Not declared

Windsurf Not declared

Gemini CLI Not declared

Cline Not declared

OpenCode Not declared

Repository health

Stars 5

License LICENSE

Default branch main

Open issues 2

Status Active

Package contents

Files included with this skill beyond the listing page.

skill md SKILL.md 3,879 B

docs SUMMARY.md 145 B

History

Jan 29, 2026 First seen on skills.sh

Sep 9, 2026 First recorded snapshot · 12 installs

SKILL.md

Eleven Labs Text-to-Speech

Generate high-quality audio from text using the Eleven Labs API. Ideal for podcast-style summaries, narration, and voice-overs.

Quick Start

# Generate audio with default voice (Rachel)
uv run scripts/generate_audio.py --text "Hello, this is a test."

# Generate from a text file
uv run scripts/generate_audio.py --file report.txt --output ~/Desktop/report.mp3

# Use a specific voice
uv run scripts/generate_audio.py --text "Breaking news..." --voice Josh

# List available voices
uv run scripts/list_voices.py

Scripts

generate_audio.py

Main script for TTS generation.

Arguments:

Argument	Description	Default
`--text`	Text content to convert	-
`--file`	Path to text file	-
`--voice`	Voice name or ID	Rachel
`--model`	Model ID	elevenmultilingualv2
`--output`	Output file path	~/Desktop/audio_TIMESTAMP.mp3

Features:

Auto-chunks text >10k characters at sentence boundaries
Concatenates chunks into single MP3
Returns JSON with metadata (file path, voice, model, char count, chunks)

list_voices.py

Fetch and display available voices.

Arguments:

Argument	Description	Default
`--all`	Show all voices (not just premade)	false
`--json`	Output as JSON	false

Curated Voices

Six voices selected for variety (see references/voices.md for details):

Voice	Style	Best For
Rachel	Calm, clear	Narration, podcasts (default)
Bella	Soft, gentle	Storytelling, meditation
Elli	Young, expressive	Casual content, tutorials
Josh	Deep, authoritative	News, professional content
Adam	Middle-aged, clear	Business, documentaries
Antoni	Warm, versatile	General purpose

Use list_voices.py to discover additional voices.

Models

Model	ID	Best For	Char Limit
Multilingual v2	`elevenmultilingualv2`	Long-form (default)	10,000
Flash v2.5	`elevenflashv2_5`	Quick, real-time	40,000
Turbo v2.5	`eleventurbov2_5`	Balanced	40,000
Eleven v3	`eleven_v3`	Maximum expression	3,000

Environment Setup

Requires ELEVENLABSAPIKEY in:

~/Library/Mobile Documents/com~apple~CloudDocs/Geoffrey/secrets/.env

Examples

Daily Summary Podcast

# Generate individual segments
uv run scripts/generate_audio.py --file weather.txt --voice Rachel --output ~/Desktop/weather.mp3
uv run scripts/generate_audio.py --file news.txt --voice Josh --output ~/Desktop/news.mp3
uv run scripts/generate_audio.py --file calendar.txt --voice Bella --output ~/Desktop/calendar.mp3

Long Report

# Auto-chunks long text, concatenates into single file
uv run scripts/generate_audio.py --file quarterly_report.txt --model eleven_turbo_v2_5 --output report.mp3

Quick Test

uv run scripts/generate_audio.py --text "Testing one two three" --voice Adam

Output

Default: ~/Desktop/audioYYYY-MM-DDHHMMSS.mp3

Script returns JSON:

{
  "success": true,
  "file": "/Users/user/Desktop/audio_2026-01-23_143022.mp3",
  "voice": "Rachel",
  "model": "eleven_multilingual_v2",
  "characters": 1234,
  "chunks": 1
}

Limitations

Character limits vary by model (see table above)
One voice per generation (multi-voice requires separate files)
Output format: MP3 only

elevenlabs-tts