AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.
bot de música programado em python com player interativo, suporte a multi-bot, comandos barra/slash, integração com last.fm e muito mais.
A local, multi-voice audiobook generator: an LLM casts every character in its own voice, kept consistent across a whole series — with voice design, per-line emotion, seven languages, and M4B / Audiobookshelf export. Runs on your own machine; you own the files. Kokoro · Qwen3-TTS.
Transform written stories into fully-voiced, multi-character audiobooks with ambient soundscapes — powered by local AI (Voicebox + Kokoro TTS + FFmpeg)
Convert EPUB/TXT/PDF/DOCX books into professionally narrated, multi-voice audiobooks (M4B/MP3/Opus/FLAC) with ACX/Audible-ready mastering
RadioFAF 69.0 FM — Authentic AI. Unscripted. Multi-voice radio powered by xAI Grok + 5 expressive voices (Leo, Sal, Ara, Rex, Eve). Live at radiofaf.com.
Automated podcast generation pipeline using a YAML-defined structure and external Text-To-Speech APIs
To associate your repository with the multi-voice topic, visit your repo's landing page and select "manage topics."