Abogen is a powerful tool that converts e-books (EPUB, PDF) or plain text into high-quality, natural-sounding audio with synchronized subtitles. Built for speed and ease, it uses the Kokoro‑82M TTS model to generate enhanced audio and subtitle outputs quickly and accurately.
Key Features
Supports multiple input formats: EPUB, PDF, and plain text (with built-in editor).
Subtitle synchronization: Generates time-aligned captions at sentence, word, or fixed-word intervals.
Voice and speed customization: Offers voice selection (e.g. male/female, language variants) and adjustable speech speed (0.1×–2.0×).
Audio export options: Outputs in WAV, FLAC, MP3, OPUS, and M4B formats (with chapters).
Chapter handling: Detects chapters in e-books or uses chapter markers in text files; can export chapters individually.
Voice mixing: Blend multiple voice models with adjustable weights to create custom voice profiles.
Cross-platform installers and Docker support: Includes installer scripts for Windows, Linux, macOS, plus Docker deployment.
Demo video creation: Integrates FFmpeg for easy export of subtitle-overlaid video.
Multilingual voices: Supports English (US/UK), Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese.
Seerah Legacy
.jpg)
.png)
.png)
.png)
.jpg)
