speech-generator

Generate speech audio from text using ElevenLabs TTS. Use when user asks to 'send voice', 'send audio message', 'create voice', 'generate speech', 'say something', 'voice message', 'send me audio', or needs TTS/narration.

Jump to install

Repository: aviz85/claude-skills-library
Last source activity: January 28, 2026 at 11:27
Detected SKILL.md language: English
Stars: 49
Forks: 14

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/aviz85/claude-skills-library --skill speech-generator

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

6 files

SKILL.md

Source instructions · Read-only preview

name: speech-generator
description: Generate speech audio from text using ElevenLabs TTS. Use when user asks to 'send voice', 'send audio message', 'create voice', 'generate speech', 'say something', 'voice message', 'send me audio', or needs TTS/narration.
version: 1.0.0
author: aviz85
tags: ["tts","speech","audio","elevenlabs","voice"]
setup: ./SETUP.md
setup_complete: false

# Speech Generator > **First time?** If `setup_complete: false` above, run `./SETUP.md` first, then set `setup_complete: true`. Generate speech audio using ElevenLabs TTS. ## Voice ID Configure your voice ID from ElevenLabs: ``` YOUR_VOICE_ID ``` > Get voice IDs from [ElevenLabs](https://elevenlabs.io/) - you can use built-in voices or clone your own. ## Prompt Guidelines (Hebrew) Write prompts as natural spoken Hebrew. Use square brackets `[...]` for speech directions. ### Direction Examples ``` [נשימה עמוקה] אוקיי, אז בואו נדבר על זה... [צחוק קל] זה ממש מצחיק שאתה אומר את זה [בהתלהבות] וואו! זה בדיוק מה שחיכיתי לו! [ברצינות] עכשיו, תקשיבו טוב... [בעצב] אני לא יודע מה להגיד... [בשקט] זה סוד, אבל... [מהר] צריך לרוץ עכשיו, אין זמן! [לאט ובבירור] חשוב. מאוד. להקשיב. [שאלה] אתה בטוח שזה מה שאתה רוצה? [הפתעה] רגע, מה?! ``` ### Natural Speech Patterns Add filler words and pauses for natural flow: - `אממ...` - `אהה...` - `כאילו...` - `נו...` - `יאללה...` - `בקיצור...` - `...` (pause) ### Example Prompt ``` [בהתלהבות] היי! מה קורה? אממ... אז רציתי לספר לכם משהו מטורף שקרה לי היום. [נשימה] אז הלכתי לקפה, וואלה, פתאום רואה את... [בשקט] אתה לא תאמין למי. [צחוק] כן, בדיוק מי שחשבת! ``` ## Commands ```bash cd ~/.claude/skills/speech-generator/scripts # Generate speech npx ts-node generate_speech.ts \ -t "[בהתלהבות] היי! מה קורה?" \ -o /path/to/output.mp3 # From file npx ts-node generate_speech.ts \ -f /path/to/script.txt \ -o /path/to/output.mp3 # List voices npx ts-node generate_speech.ts --list-voices ``` ## Options | Option | Short | Default | |--------|-------|---------| | `--text` | `-t` | Text to speak | | `--file` | `-f` | Read from file | | `--output` | `-o` | Output path (required) | | `--voice` | `-v` | Voice ID | | `--speed` | | 1.0 | | `--stability` | | 0.5 | | `--similarity` | | 0.75 |

View on GitHub

Back to search Back to installation

WhatsApp automation (Green API primary, WAHA fallback). Use for: send/receive messages, send voice/images/files, retrieve incoming messages (text, voice, images), transcribe voice messages. WAME = 'WhatsApp ME' = send me by WhatsApp.

2026-07-08

quick-voice

Spin up an instant browser voice session (OpenAI Realtime gpt-realtime-2) to close a topic in a short conversation instead of working through documents. Generic & white-label - works for any process. Supports live data work (read/update files, JSON, run commands), and distill mode (no tools, ends with a structured deliverable). Has a generic canvas that can display images, markdown, code, html, json, video, audio - perfect for "let's go over X" flows where the agent shows you items one by one and you react in real time. Use when user says "let's close this in a voice call", "run a quick voice session about X", "תפעיל שיחה קולית", "let's go over the [images/leads/PRs/files/notes]", or when a task is faster as a 3-minute conversation than as a document edit.

2026-07-07

ten-by-ten

The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.

2026-06-17

View all from this repository

speech-generator

Source facts

Install options

Review the source files

More from this repository

More from this repository