Convert AI chat messages into spoken audio files using OpenAI's TTS service.
Install
mkdir -p .claude/skills/voice && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14645" && unzip -o skill.zip -d .claude/skills/voice && rm skill.zipInstalls to .claude/skills/voice
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Generate voice responses using OpenAI's text-to-speech API.Key capabilities
- →Generate voice responses using OpenAI's text-to-speech API
- →Select different voice styles
- →Choose between different quality models
- →Adjust speech speed
- →Specify audio output format
- →Save voice files to a local directory
How it works
The skill executes a shell command that calls a script to generate voice responses using OpenAI's text-to-speech API, allowing customization of voice, model, speed, and format.
Inputs & outputs
When to use voice
- →Generating voice responses
- →Customizing voice pitch and speed
- →Creating audio logs from chat
About this skill
Voice Skill
Generate voice responses using OpenAI's text-to-speech API.
When to Use
- Primary response method for this workspace
- When communicating with the user
- Voice messages ARE the response (chat text = transcript only)
Command
/Users/erezfern/Workspace/jarvis/.claude/skills/voice/jarvis_voice.sh --voice echo "[message]"
Options
| Option | Values | Default | Description |
|---|---|---|---|
--voice | alloy, echo, fable, onyx, nova, shimmer | echo | Voice style |
--model | tts-1, tts-1-hd | tts-1 | Quality (hd = higher quality) |
--speed | 0.25 - 4.0 | 1.0 | Speech speed |
--format | mp3, opus, aac, flac, wav | mp3 | Audio format |
Output Location
Voice files are saved to:
/Users/erezfern/Workspace/jarvis/.claude/skills/voice/output/
Examples
# Standard response
/Users/erezfern/Workspace/jarvis/.claude/skills/voice/jarvis_voice.sh --voice echo "Task completed successfully."
# Different voice
/Users/erezfern/Workspace/jarvis/.claude/skills/voice/jarvis_voice.sh --voice nova "Here's what I found."
# Faster speech
/Users/erezfern/Workspace/jarvis/.claude/skills/voice/jarvis_voice.sh --voice echo --speed 1.2 "Quick update for you."
Guidelines
- Keep messages concise (1-3 sentences ideal)
- Use echo voice by default (professional, clear)
- Complex information goes in documents, not voice
- Voice = complete response (don't add extra text in chat)
When not to use it
- →When voice messages are not the primary response method
- →When complex information needs to be conveyed (use documents instead)
- →When the user does not want a voice response
Limitations
- →Messages should be concise (1-3 sentences ideal)
- →Complex information should be conveyed in documents, not voice
- →The output directory for voice files is fixed
How it compares
This skill provides a direct interface to OpenAI's text-to-speech API with customizable parameters, enabling automated voice generation unlike manual text-to-speech tools.
Compared to similar skills
voice side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| voice (this skill) | 0 | 7mo | Review | Beginner |
| himalaya | 50 | 3mo | Review | Intermediate |
| discord-send-message | 7 | 10mo | Review | Intermediate |
| voicemode | 8 | 2mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
himalaya
openclaw
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
discord-send-message
Nice-Wolf-Studio
Send messages to Discord channels via the Discord API. Use this skill when the user wants to send text messages, notifications, or formatted content to a Discord channel.
voicemode
mbailey
This skill provides voice interaction capabilities for AI assistants. This skill should be used when users mention voice mode, want to have voice conversations, speak with Claude, check voice service status, or manage voice services like Whisper and Kokoro.
officeemail-management
harperreed
Handle email tasks (checking inbox, drafting replies, managing threads, adding events to calendar). Use when working with emails to prevent common mistakes like broken threading or missing recipients.
ask-user-question
MemTensor
Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.
campaign-orchestration
ernijsansons
Create and execute personalized multi-channel campaigns across email, LinkedIn, and phone based on intelligence gathering triggers. Use when planning outreach sequences, optimizing engagement strategies, or executing systematic follow-up campaigns.