How do I use gTTS to save an MP3 file from text in Python?

Import the gTTS module, create a gTTS object with your text, and call the save() method with a filename. Example: `from gtts import gTTS; tts = gTTS('hello'); tts.save('hello.mp3')` as shown in the README.

Is gTTS completely free, and are there any usage limits?

gTTS is free since it uses Google Translate's public API, but it's unofficial and subject to Google's terms. While no direct costs exist, usage might be rate-limited or altered without warning, so it's not reliable for high-volume production.

gTTS or Google Cloud Text-to-Speech: which is better for a serious project?

gTTS is ideal for prototyping, personal use, or avoiding cloud setup due to its simplicity and zero cost. Google Cloud Text-to-Speech is better for production apps needing reliability, advanced features, and official support with SLAs.

Can I change languages and accents with gTTS?

Yes, specify the 'lang' parameter (e.g., 'en' for English, 'es' for Spanish) to switch languages, but voice options are limited to Google Translate's available selections, with fewer customization features compared to paid services.

How does gTTS handle very long documents without breaking?

It uses a customizable tokenizer to split text into sentences for synthesis, maintaining intonation. You can pass unlimited text directly, and the library manages chunking internally, as noted in the features section.

What are good offline alternatives to gTTS for Python?

For offline use, consider pyttsx3 which uses system TTS engines, or for more features, cloud-based alternatives like Amazon Polly, though they require accounts and may have costs associated.

Open-Awesome

gtts

MITPythonv2.5.4

Python library and CLI tool to interface with Google Translate's text-to-speech API for generating MP3 audio from text.

Visit Website GitHub

2.6k stars389 forks0 contributors

What is gtts?

gTTS is a Python library and command-line tool that interfaces with Google Translate's text-to-speech API to convert text into spoken MP3 audio. It solves the problem of adding speech synthesis to applications without requiring official Google Cloud services or complex setup. The tool handles text tokenization and preprocessing to produce natural-sounding speech from unlimited text lengths.

Target Audience

Python developers and system administrators who need to generate speech audio from text for applications, automation scripts, or command-line workflows without relying on paid cloud services.

Value Proposition

Developers choose gTTS for its simplicity, zero-cost access to Google's speech synthesis, and dual library/CLI interface. It provides an unofficial, lightweight alternative to Google Cloud Text-to-Speech, ideal for prototyping, personal projects, or scenarios where cloud account setup is impractical.

Overview

Python library and CLI tool to interface with Google Translate's text-to-speech API

Use Cases

Best For

Adding text-to-speech functionality to Python applications
Generating audio files from text for podcasts or voiceovers
Creating command-line scripts that output spoken audio
Prototyping speech features without Google Cloud setup
Processing long text documents into speech with proper intonation
Implementing pronunciation corrections in speech synthesis

Not Ideal For

Production applications requiring official API support and service-level agreements
Projects needing advanced voice customization options like pitch, speed, or emotional tone control
Systems that must operate offline or in environments with restricted internet connectivity

Pros & Cons

Pros

Easy Integration

Offers both a Python library and CLI tool, enabling quick speech synthesis with minimal setup, as demonstrated in the README's quickstart examples.

Handles Unlimited Text

Customizable sentence tokenizer processes long texts while maintaining proper intonation, abbreviations, and decimal formatting, allowing synthesis of entire documents.

Cost-Free Access

Leverages Google Translate's free text-to-speech API without requiring a Google Cloud account, making it accessible for personal and non-commercial projects.

Customizable Preprocessing

Includes text pre-processors for pronunciation corrections and custom manipulation, providing flexibility in preparing text for natural-sounding speech.

Cons

Unofficial and Unstable

Relies on an undocumented Google Translate API, so breaking upstream changes can occur without notice, as warned in the disclaimer, risking application reliability.

Limited Feature Set

Lacks advanced options available in Google Cloud Text-to-Speech, such as detailed voice selection, audio parameter tuning, and emotional speech synthesis.

Internet Dependency

Requires active internet connectivity to access Google's servers, making it unsuitable for offline use or applications in low-bandwidth environments.

Open Source Alternative To

gtts is an open-source alternative to the following products:

Google Cloud Text-to-Speech

A cloud service that converts text into natural-sounding speech using Google's neural network technology.

Frequently Asked Questions

Related Projects

beets

music library manager and MusicBrainz tagger

Stars15,821

Forks2,158

Last commit2 days ago

moviepy

Video editing with Python

Stars15,011

Forks2,125

Last commit1 month ago

pydub

Manipulate audio with a simple and easy high level interface

Stars9,802

Forks1,138

Last commit7 months ago

Librosa

Python library for audio and music analysis

Stars8,698

Forks1,089

Last commit17 days ago

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub