dvchd

dvchd / story2audio

Public

🎧 Chuyển văn bản thành âm thanh chất lượng cao với Live Streaming, Phụ đề trực tiếp và 7 ngôn ngữ. Miễn phí, không giới hạn.

story2audio.hoctuthien.com
27
7
100% credibility
Found Apr 19, 2026 at 27 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Story2Audio is an open-source web app that converts text into natural-sounding speech with live subtitles in multiple languages using free TTS services.

How It Works

1
🔍 Discover the tool

You find Story2Audio online, a free way to turn any text like stories or articles into natural audio with subtitles.

2
🌐 Visit the demo

Head to the ready-to-use website and paste your text into the simple box.

3
🎙️ Pick voice and play

Choose a language and friendly voice, then click to start – hear it read aloud live with captions popping up right away.

4
👂 Listen with subtitles

Relax as the voice reads your text naturally, following along with real-time subtitles that match every word.

5
💾 Save your audio

Download the full sound file and subtitle files with one click to listen offline anytime.

6
Want more?
✅
Stick online

Keep using the free website unlimited, no setup needed.

🏠
Run at home

Follow easy steps to launch it on your computer for personal use.

🎉 Stories come alive!

Now any text turns into enjoyable audio with subtitles, free and ready whenever you want.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 27 to 27 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is story2audio?

Story2audio is a Python-based FastAPI server that converts any text—from short notes to full novels—into high-quality (cao) audio using free Microsoft Edge TTS. It streams live audio playback instantly while generating, pairs it with real-time subtitles in sync, and supports seven languages including Vietnamese, English, Japanese, Chinese, Korean, French, and German. Users get MP3 downloads, SRT/VTT subtitles, and smart caching for instant replays, solving the hassle of paid APIs or waiting for long-form audio.

Why is it gaining traction?

It stands out with unlimited free usage—no API keys or quotas—plus live streaming and subtitles that update sentence-by-sentence for immersive listening. Docker Compose deploys it in seconds to VPS or platforms like Coolify/Railway, and the full REST API (with Swagger docs) lets you integrate text-to-audio endpoints easily. Developers hook on the natural neural voices and multi-language support without vendor lock-in.

Who should use this?

Backend devs building podcasts, audiobooks, or reading apps needing cheap TTS integration. Content platforms automating audio from articles or stories in multiple languages. Multilingual teams creating voiceovers for education tools or accessibility features.

Verdict

Grab it if you need free, self-hosted TTS with live streaming—solid docs and Docker make setup trivial. At 27 stars and 1.0% credibility, it's early-stage so test thoroughly before production, but promising for Python stacks avoiding ElevenLabs costs.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.