docs-to-voice

Convert text to audio with sentence timelines and subtitle files.

4|2|Updated Feb 25, 2026

Search Tags:#automation #timeline #text-to-speech #audio #tts #subtitle #model-studio

Ready to run

npx skills add https://github.com/LaiTszKin/apollo-toolkit --skill docs-to-voice

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: docs-to-voice
Source: https://github.com/LaiTszKin/apollo-toolkit/tree/main/docs-to-voice
Command: npx skills add https://github.com/LaiTszKin/apollo-toolkit --skill docs-to-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Converts text content into audio files and synchronize sentence-level timelines with subtitle files, empowering quick voice-ready outputs from documents or notes.

Core Features & Use Cases

Generate audio from raw text or text files using two modes: macOS say and Alibaba Cloud Model Studio API.
Produce sentence-level timelines (.timeline.json) and subtitle tracks (.srt) alongside the audio for easy video and documentation workflows.
Use case: turn a long article into shareable audio with searchable, timestamped captions for accessibility and faster content consumption.

Quick Start

Run the docs-to-voice skill on a project to convert text into audio with timeline-ready outputs.

Frequently Asked Questions about docs-to-voice

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

FAQPage Schema

How do I convert text to speech and generate subtitle files automatically?▼

To convert text to speech and generate subtitle files, docs-to-voice processes raw text and outputs audio alongside per-sentence timeline JSON and SRT subtitle tracks for immediate video and documentation workflows.

Can I use macOS say command for text-to-speech audio generation?▼

Yes, you can use the macOS say command for text-to-speech audio generation. The Skill supports a 'say' mode alongside an Alibaba Cloud Model Studio API mode, both configurable via environment variables in the .env file.

What is the best way to handle long text for TTS audio processing?▼

The best way to handle long text for TTS audio processing is by using configurable chunking and model-length discovery. The Skill automatically splits long articles and concatenates the final audio outputs seamlessly.

Does this text-to-speech tool output SRT subtitle tracks for video workflows?▼

Yes, this text-to-speech tool outputs SRT subtitle tracks for video workflows. It generates sentence-level timelines and subtitle files under the project directory, providing timestamped captions for accessibility.

Do I need an API key to use Alibaba Cloud Model Studio for audio generation?▼

Yes, you need an API key to use Alibaba Cloud Model Studio for audio generation. You must configure your endpoints, API keys, and preferred voices using environment variables in the .env file before processing.