multi-voice

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.

Convert EPUB/TXT/PDF/DOCX books into professionally narrated, multi-voice audiobooks (M4B/MP3/Opus/FLAC/WAV), mastered to the ACX audio spec

Transform written stories into fully-voiced, multi-character audiobooks with ambient soundscapes — powered by local AI (Voicebox + Kokoro TTS + FFmpeg)

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.

Voxprint AI Movie Dubber — offline AI dubbing for movies and series: adds a dubbed audio track in your language with voices cloned from the film or open CC0 voices; video untouched, original track kept. Windows 11 + NVIDIA. Part of the Voxprint AI Media Suite.

Voxprint AI Audiobook Builder — offline audiobook narration and voice cloning: narrate TXT/FB2/EPUB in multi-voice with your own or open CC0 voices. Windows 11 + NVIDIA, Linux experimental. Part of the Voxprint AI Media Suite.

Automated podcast generation pipeline using a YAML-defined structure and external Text-To-Speech APIs

Offline AI audiobook maker and multi-voice text to speech for Mac — audiobooks, video voice-overs, audio dramas and podcasts. Local models; your text, voices and audio never leave your computer.