How do I install the Text To Speech skill?

Run npx skillmds@latest add dalehurley/text-to-speech in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Text To Speech safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Text To Speech?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Text To Speech free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Text To Speech?

dalehurley (@dalehurley) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Text To Speech by dalehurley — Agent Skill

Name: Text To Speech
Author: dalehurley

Text To Speech

Produce actual audio output from the computer's speakers using text-to-speech. Use this skill when the user asks to speak, say something out loud, talk, vocalize, read aloud, announce, play audio from text, or produce voice output. Can use OS-native commands (macOS say, Linux espeak) or high-quality API-based TTS (OpenAI). The key point: this MUST produce real sound, not just text.

dalehurley Updated Sep 17, 2026

File contents

Skill: text-to-speech

When to Use

Use this skill when the user asks to:

Say something out loud / speak / talk
Read text aloud or announce something
Generate audio from text
Create a voice message or spoken output
Use text-to-speech / TTS
Produce audible output from the computer speakers

CRITICAL: This skill produces REAL AUDIO from the speakers. NOT just text.

Input Parameters

Parameter	Required	Description	Example
`text_content`	Yes	The text to speak out loud	hello I am P-H-P Bot

Procedure

Extract the text content from the user's request
Try the simplest approach first — use the OS built-in TTS:
- macOS: say "{{TEXT_CONTENT}}" (zero dependencies, instant)
- Linux: espeak "{{TEXT_CONTENT}}" or spd-say "{{TEXT_CONTENT}}"
- Verify it worked (exit code 0)
If higher quality is needed or the simple approach fails, escalate:
- Check for an OpenAI API key: get_keys → search_computer → ask_user
- Generate speech via API: curl the OpenAI TTS endpoint, save to MP3
- Play the MP3: afplay (macOS) or mpv/aplay (Linux)
Confirm to the user that audio was played from the speakers

Reference Commands

# Simplest: macOS built-in (try this first)
say "hello I am P-H-P Bot"

# With voice selection
say -v Samantha "hello I am P-H-P Bot"

# Higher quality: OpenAI TTS API → play result
curl -s https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer ${OPENAI_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","input":"hello I am P-H-P Bot","voice":"alloy"}' \
  --output /tmp/speech.mp3 && afplay /tmp/speech.mp3

Example

talk out loud and say "hello I am P-H-P Bot"
say "good morning" out loud
speak the following text: welcome to PHP Bot
read this aloud: the quick brown fox

---name: text-to-speechdescription: Produce actual audio output from the computer's speakers using text-to-speech. Use this skill when the user asks to speak, say something out loud, talk, vocalize, read aloud, announce, play audio from text, or produce voice output. Can use OS-native commands (macOS say, Linux espeak) or high-quality API-based TTS (OpenAI). The key point: this MUST produce real sound, not just text.---# Skill: text-to-speech## When to UseUse this skill when the user asks to:- Say something out loud / speak / talk- Read text aloud or announce something- Generate audio from text- Create a voice message or spoken output- Use text-to-speech / TTS- Produce audible output from the computer speakersCRITICAL: This skill produces REAL AUDIO from the speakers. NOT just text.## Input Parameters| Parameter | Required | Description | Example || -------------- | -------- | -------------------------- | -------------------- || `text_content` | Yes | The text to speak out loud | hello I am P-H-P Bot |## Procedure1. Extract the text content from the user's request2. Try the simplest approach first — use the OS built-in TTS: - **macOS**: `say "{{TEXT_CONTENT}}"` (zero dependencies, instant) - **Linux**: `espeak "{{TEXT_CONTENT}}"` or `spd-say "{{TEXT_CONTENT}}"` - Verify it worked (exit code 0)3. If higher quality is needed or the simple approach fails, escalate: - Check for an OpenAI API key: `get_keys` → `search_computer` → `ask_user` - Generate speech via API: `curl` the OpenAI TTS endpoint, save to MP3 - Play the MP3: `afplay` (macOS) or `mpv`/`aplay` (Linux)4. Confirm to the user that audio was played from the speakers## Reference Commands```bash# Simplest: macOS built-in (try this first)say "hello I am P-H-P Bot"# With voice selectionsay -v Samantha "hello I am P-H-P Bot"# Higher quality: OpenAI TTS API → play resultcurl -s https://api.openai.com/v1/audio/speech \ -H "Authorization: Bearer ${OPENAI_API_KEY}" \ -H "Content-Type: application/json" \ -d '{"model":"tts-1","input":"hello I am P-H-P Bot","voice":"alloy"}' \ --output /tmp/speech.mp3 && afplay /tmp/speech.mp3```## Example```talk out loud and say "hello I am P-H-P Bot"say "good morning" out loudspeak the following text: welcome to PHP Botread this aloud: the quick brown fox```

Frequently asked questions