gTTS and tts-wrapper
gTTS is a single-provider implementation that directly wraps Google Translate's API, while tts-wrapper is a multi-provider abstraction layer that could encompass gTTS-like functionality—making them complements where tts-wrapper offers the unified interface that gTTS serves as one concrete backend for.
About gTTS
pndurette/gTTS
Python library and CLI tool to interface with Google Translate's text-to-speech API
Supports unlimited text length through intelligent sentence tokenization that preserves intonation and handles abbreviations, decimals, and special cases. Output is flexible—write directly to MP3 files, file-like objects for audio processing pipelines, or stdout for streaming. Includes customizable text pre-processors for pronunciation corrections and leverages Google Translate's undocumented speech endpoint rather than the official Cloud API.
About tts-wrapper
mediatechlab/tts-wrapper
TTS-Wrapper makes it easier to use text-to-speech APIs by providing a unified and easy-to-use interface.
Supports six TTS providers (AWS Polly, Google, Microsoft, IBM Watson, PicoTTS, SAPI) with pluggable client architecture that abstracts away different authentication methods and APIs. Features SSML markup support with service-specific boilerplate generation, voice/language selection, and flexible output formats (WAV, MP3). Optional dependencies per service reduce installation footprint while maintaining a consistent `synth()` interface across all backends.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work