krishagelkrishagel/geoffrey/skills/elevenlabs-tts/SKILL.md

elevenlabs-tts

Skill9 starsChanged 11 months agoMITView on GitHub

Generate high-quality audio from text using Eleven Labs API. Use for podcasts, narration, voice-overs, and audio summaries.

Reads credentials

9 other projects use a version of this.

Adopted by

Most recently taken up by

jechearte/skillstheir own version, first seen Nov 8, 2026
shaharsha/claude-skillstheir own version, first seen Oct 24, 2026
AngelescuCiprian/claude-skillstheir own version, first seen Aug 22, 2026
glebis/claude-skillstheir own version, first seen Jul 1, 2026
JAVICHILEON/claude---Skillstheir own version, first seen Jul 1, 2026
nikunj812/claude-skilltheir own version, first seen Jul 1, 2026

Used with

Projects with it also use agency-docs-updater, brand-agency and 10 more.

Other files people use alongside this one.

KISHOR403Skill
agency-docs-updater
End-to-end pipeline for publishing Claude Code lab meetings. Automatically finds/creates Fathom transcript, downloads video, uploads to YouTube, generates fact-checked Russian summary, creates MDX documentation, and pushes to agency-docs for Vercel deployment. Single invocation replaces 5+ manual steps.
Also in 3 projects that use this
KISHOR403Skill
brand-agency
Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when brand colors, visual formatting, neobrutalism style, or Agency design standards apply. Keywords - branding, corporate identity, visual identity, styling, brand colors, typography, visual formatting, visual design, neobrutalism.
Also in 3 projects that use this
+10 more from KISHOR403

Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
glebis/claude-skills★ 410same name
emanueleielo/ciana-parrot★ 77same name
shaharsha/claude-skills★ 6same name
jechearte/skills★ 1same name
yourkenike/ciana-parrot★ 1same name
AngelescuCiprian/claude-skills★ 0same name
JAVICHILEON/claude---Skills★ 0same name
KISHOR403/claude-skills★ 0same name
nikunj812/claude-skill★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- assistant-architectSkill
- cfo-briefingSkill
- clawdbot-monitorSkill
- docxSkill
- drafts-managerSkill
- freshservice-managerSkill
- google-workspaceSkill
- image-genSkill
- knowledge-managerSkill
- legislative-trackerSkill
- local-ttsSkill
- morning-briefingSkill
- multi-model-researchSkill
- obsidian-managerSkill
- omnifocus-managerSkill
- pai-monitorSkill
- pdfSkill
- pdf-to-markdownSkill
- personal-strategic-planningSkill
- pptxSkill
- presentation-masterSkill
- psd-athleticsSkill
- psd-brand-guidelinesSkill
- psd-instructional-visionSkill
- redrover-managerSkill
- researchSkill
- seven-advisorsSkill
- skill-creatorSkill
- sop-creatorSkill
- strategic-planning-managerSkill
- writerSkill
- xlsxSkill

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

0
Common
Most of the 7 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Use list_voices.py to discover additional voices.
line 79

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

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	eleven_multilingual_v2
`--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	`eleven_multilingual_v2`	Long-form (default)	10,000
Flash v2.5	`eleven_flash_v2_5`	Quick, real-time	40,000
Turbo v2.5	`eleven_turbo_v2_5`	Balanced	40,000
Eleven v3	`eleven_v3`	Maximum expression	3,000

Environment Setup

Requires ELEVENLABS_API_KEY 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/audio_YYYY-MM-DD_HHMMSS.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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free