gtts

Convert long text into a single MP3 audio file using Google's gTTS.

Updated Jan 15, 2026
One-click install
npx skills add https://github.com/KaiserWhoLearns/skillsbench --skill gtts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gtts
Source: https://github.com/KaiserWhoLearns/skillsbench/tree/main/tasks/pg-essay-to-audiobook/environment/skills/gtts
Command: npx skills add https://github.com/KaiserWhoLearns/skillsbench --skill gtts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts written content into spoken audio using Google's gTTS, enabling audiobook-like outputs, podcasts, and accessible narration for long texts without manual recording.

Core Features & Use Cases

  • Text-to-speech conversion via gTTS in Python for quick prototyping.
  • Long-text handling by chunking at sentence boundaries and concatenating segments with pydub.
  • Use Case: turn a long article or report into a ready-to-listen MP3 file.

Quick Start

Install gtts and pydub, then run a Python script that chunks long text at sentence boundaries and concatenates the results into an MP3 file.

Frequently Asked Questions about gtts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert long text to speech in Python without hitting API limits?

Python text-to-speech conversion for long texts handles API limits by chunking text at sentence boundaries and concatenating audio segments with pydub into a single MP3 file. This avoids length restrictions while maintaining continuous narration.

What's the best way to turn a long article into an audiobook MP3 using Python?

Turning articles into audiobook MP3s is best achieved by using Python gTTS for speech synthesis and pydub for audio concatenation. The process splits text at sentence boundaries, synthesizes chunks, and merges them into a shareable audio file.

Do I need pydub to use gTTS for generating podcasts from long documents?

Yes, pydub is required for generating podcasts from long documents because gTTS has text length limitations. Pydub concatenates the individual speech segments created from sentence-boundary text chunks into one final MP3 output.

Can I use gTTS to generate podcast audio from reports automatically?

Yes, gTTS can automatically generate podcast audio from reports. By scripting text-to-speech conversion in Python, written reports are transformed into ready-to-listen MP3 files without manual recording.

Does gTTS support processing long text files for speech synthesis?

gTTS supports long text files for speech synthesis when combined with chunking logic. By splitting text at sentence boundaries before synthesis and concatenating the resulting audio with pydub, it effectively processes lengthy documents into a single MP3.

Why does my gTTS Python script fail on long text inputs?

gTTS scripts fail on long text inputs due to character limits in the speech synthesis API. Chunking the text at sentence boundaries before passing it to gTTS and merging the outputs with pydub resolves this limitation.