Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Modified version of Chatterbox that accepts text files as input and no character restrictions. I use it to make audiobooks, especially for my kids.
| Date | Stars |
|---|---|
| 2026-07-24 | 573 |
| 2026-07-25 | 573 |
| 2026-07-28 | 573 |
| 2026-07-30 | 573 |
| 2026-08-06 | 573 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 🚀 Chatterbox-TTS-Extended — All Features & Technical Explanations
Chatterbox-TTS-Extended is a *power-user TTS pipeline* for advanced single and batch speech synthesis, voice conversion, and artifact-reduced audio generation. It is based on [Chatterbox-TTS](https://github.com/resemble-ai/chatterbox), but adds:
- **Multi-file input & batch output**
- **Custom candidate generation & validation**
- **Rich audio post-processing**
- **Whisper/faster-whisper validation**
- **Voice conversion (VC) tab**
- **Full-featured persistent UI with parallelism and artifact reduction**
- **Optional audio denoising with pyrnnoise - removes most artifacts**
---
## 📋 Table of Contents
- [Feature Summary Table](#feature-summary-table)
- [Text Input & File Handling](#text-input--file-handling)
- [Reference Audio](#reference-audio)
- [Voice/Emotion/Synthesis Controls](#voiceemotionsynthesis-controls)
- [Batching, Chunking & Grouping](#batching-chunking--grouping)
- [Text Preprocessing](#text-preprocessing)
- [Audio Post-Processing](#audio-post-processing)
- [Export & Output Options](#export--output-options)
- [Generation Logic & Quality Control](#generation-logic--quality-control)
- [Whisper Sync & Validation](#whisper-sync--validation)
- [Parallel Processing & Performance](#parallel-processing--performance)
- [Persistent Settings & UI](#persistent-settings--ui)
- [🎙️ Voice Conversion (VC) Tab](#️-voice-conversion-vc-tab)
- [Tips & Troubleshooting](#tips--troubleshooting)
- [Installation](#-installation)
- [Feedback & Contributions](#-feedback--contributions)
- [Known Bugs](#known-bugs)
---
## Feature Summary Table
| Feature | UI Exposed? | Script Logic |
| ----------------------------------------- | ------------- | ------------ |
| Text input (box + multi-file upload) | ✔ | Yes |
| Reference audio (conditioning) | ✔ | Yes |
| Separate/merge file output | ✔ | Yes |
| Emotion, CFG, temperature, seed | ✔ | Yes |
| Batch/smart-append/split (sentences) | ✔ | Yes |
| Sound word remove/replace | ✔ | Yes |
| Inline reference number removal | ✔ | Yes |
| Dot-letter ("J.R.R.") correction | ✔ | Yes |
| Lowercase & whitespace normalization | ✔ | Yes |
| Auto-Editor post-processing | ✔ | Yes |
| **pyrnnoise denoising (RNNoise)** | ✔ | Yes |
| FFmpeg normalization (EBU/peak) | ✔ | Yes |
| WAV/MP3/FLAC export | ✔ | Yes |
| Candidates per chunk, retries, fallback | ✔ | Yes |
| Parallelism (workers) | ✔ | Yes |
| Whisper/faster-whisper backend | ✔ | Yes |
| Persistent settings (JSON/CSV per output) | ✔ | Yes |
| Settings load/save in UI | ✔ | Yes |
| Audio preview & download | ✔ | Yes |
| Help/Instructions | ✔ (Accordion) | Yes |
| Voice Conversion (VC tab) | ✔ | Yes |
---
## Text Input & File Handling
- **Text box:** For direct text entry (single or multi-line).
- **Multi-file upload:** Drag-and-drop any number of `.txt` files.
- Choose to merge them into one audio or process **each as a separate output** (toggle in the UI).
- Outputs are named for sorting and reproducibility.
- **Reference audio input:** Upload or record a sample to condition the generated voice.
- **Settings file support:** Load or save all UI settings as JSON for easy workflow repeatability.
---
## ReferExcerpt of 11,203 characters
Read on GitHub
111
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d1f670526fed65c1, topic:text-to-speech, topic:tts, topic:voice-cloning