Tts
Speak or render text to speech locally.
Install
npx skills add codewhale-hq/Codewhale --skill tts -g -a claude-code -y- Repository
- codewhale-hq/Codewhale41.2k
- Category
- Media
- Updated
- 3d ago
- License
- MIT
- Context cost
- Lightabout 232 tokens
- Runs scripts
- No, instructions only
What it does
Speak or render text to speech locally. Use when: read aloud, speak, voice output, tts, text to speech, or an audio version of text.
Text to Speech
When to use
Reading text aloud or rendering speech audio files, using only the voices already on the machine.
Setup
No account or API key. Pick the platform command; fail loud when the
Linux engine is missing (sudo apt install speech-dispatcher or espeak-ng):
- macOS:
say -v Samantha -o out.aiff "text"(list voices:say -v '?') - Linux:
spd-say "text"orespeak-ng -w out.wav "text" - Windows: PowerShell
System.Speech.Synthesis.SpeechSynthesizer
Workflow
- Keep utterances short; split long text at paragraph breaks.
- Confirm voice and speed when the user cares; otherwise default voice, normal rate.
- For files, report the path, format, and duration.
Non-goals
- Do not clone voices or impersonate a real person.
- Do not call cloud TTS APIs (different cost and privacy posture, ask first).
- Do not play audio unprompted in shared environments; render a file instead.
