Google Tts

This wraps the Google Cloud Text-to-Speech API so you can narrate documents, generate voiceovers, or create two-host podcast conversations from written content. It handles chunking for longer documents, supports 40+ languages with Neural2, WaveNet, and Studio voices, and can stitch multi-speaker JSON scripts into a single audio file with different voices per speaker. The podcast mode is clever if you want to turn a technical doc into a conversational audio format. Setup needs a Google Cloud API key and ffmpeg for longer files. Output defaults to MP3 in your Downloads folder. Neural2 voices hit a good balance between quality and cost at around $4 per million characters.

skills.sh installs: 344
GitHub stars: 454
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sanjay3290/ai-skills --skill google-tts --agent claude-code

Installs into .claude/skills of the current project.

Files

Google Cloud Text-to-Speech

Converts text and documents into audio using Google Cloud TTS API. Supports Neural2, WaveNet, Studio, and Standard voices across 40+ languages.

Setup

API key via GOOGLE_TTS_API_KEY env var or skills/google-tts/config.json with {"api_key": "..."}. Requires ffmpeg for multi-chunk documents. Optional: pip install PyPDF2 python-docx for PDF/DOCX.

Commands

List Voices

python skills/google-tts/scripts/google_tts.py voices --language en-US --type Neural2
python skills/google-tts/scripts/google_tts.py voices --json

Text-to-Speech

# From text or document (PDF, DOCX, MD, TXT)
python skills/google-tts/scripts/google_tts.py tts --text "Hello world" --output ~/Downloads/hello.mp3
python skills/google-tts/scripts/google_tts.py tts --file /path/to/doc.pdf --output ~/Downloads/narration.mp3

# With voice, rate, pitch, encoding options
python skills/google-tts/scripts/google_tts.py tts --file doc.md --voice en-US-Neural2-F --rate 0.9 --encoding MP3 --output ~/Downloads/out.mp3