OpenParable
Skip to content
← Back to skills

Tts

Apps & Automation
tts

Tts is an Agent Skill for apps & automation published in the mikeyobrien/rho repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Text-to-speech on Linux -- make the device speak text aloud. Use for voice announcements, reading content aloud, or accessibility.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/mikeyobrien/rho/blob/HEAD/platforms/linux/skills/tts/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/tts, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Text-to-Speech

espeak / espeak-ng

Install

# Debian/Ubuntu
sudo apt install espeak-ng

# Arch
sudo pacman -S espeak-ng

# Fedora
sudo dnf install espeak-ng

Speak text

espeak "Hello, this is a test"
espeak-ng "Hello, this is a test"

Pipe text

echo "Hello world" | espeak
cat article.txt | espeak

Choose a voice/language

espeak -v en "English"
espeak -v en-us "American English"
espeak -v fr "Bonjour"

List available voices

espeak --voices
espeak --voices=en   # English voices only

Adjust speed (words per minute)

espeak -s 200 "Speaking faster"
espeak -s 100 "Speaking slower"

Adjust pitch (0-99)

espeak -p 80 "Higher pitch"
espeak -p 20 "Lower pitch"

Save to audio file

espeak -w output.wav "Text to save"

speech-dispatcher (spd-say) -- alternative

# Install
sudo apt install speech-dispatcher

# Speak
spd-say "Hello world"

# Set rate (-100 to 100)
spd-say -r 50 "Faster"

# Set voice
spd-say -t female1 "Hello"

# Stop speech
spd-say -S

piper -- neural TTS (higher quality)

For higher quality offline TTS, consider piper:

echo "Hello world" | piper --model en_US-lessac-medium --output_file output.wav
aplay output.wav

Command blocks until speech completes (espeak, spd-say). On headless systems, audio output requires ALSA or PulseAudio.