pndurette/gTTS

Health v2 · maintenance only

Adoption not part of the score

2627 stars · 389 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

gTTS is a Python library and CLI tool that interfaces with Google Translate's text-to-speech API to generate spoken MP3 audio from text. It supports unlimited text lengths via sentence tokenization and customizable text pre-processors for pronunciation corrections.

Use cases

• convert text to speech mp3 in python
• read a long article aloud as audio
• generate voice audio files from text
• add text-to-speech to a python script
• pronounce words for a language learning app
• save spoken audio to stdout or a file-like object

When to choose

• you want a simple, free way to synthesize speech via Google Translate's endpoint
• you need both a Python API and a command-line tool
• you need to handle long text with proper sentence tokenization

When to avoid

• you need a supported, SLA-backed cloud TTS service (use Google Cloud Text-to-Speech)
• you need offline or on-device speech synthesis
• you cannot tolerate breakage from undocumented upstream API changes

Facets

library · maturity stable

tts cli audio-processing speech-processing developer-tools python cli cross-platform google-translate mp3 text-to-speech python-library speech-api natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="pndurette/gTTS")