Folivox

Folivox is an audiobook generator that converts ebooks into chaptered audiobooks using local or online engines.

Folivox turns books into finished audiobooks using either a free local model or online engines with your own API key. It supports FB2, EPUB, DOCX, PDF, and TXT inputs, and outputs .m4b or .mp3 files with chapters and metadata. The software prepares text for speech, handles stress and pronunciations, and uses Whisper for quality control. It runs on macOS, Linux, and Windows via a web studio or command line interface. Designed for long books, it includes a crash-safe journal and supports Apple Silicon, NVIDIA CUDA, or CPU hardware.

Folivox at a glance

Best for: Writer
Runs on: macOS, Windows, Linux, Web, CLI
Pricing: Free local engine with no limits; paid online engines use your own API keys with optional spending caps.
Released: October 2026
Category: AI audio tool
Website: github.com/vatavale/folivox

Key features

Converts FB2, EPUB, DOCX, PDF, and TXT to audiobook files
Uses CosyVoice 3 for local and offline voice cloning
Supports ElevenLabs, OpenAI, Gemini, and Cartesia online engines
Performs text cleanup for numbers, dates, and abbreviations
Includes automated quality control using Whisper
Generates chapter markers, covers, and metadata
Maintains a crash-safe journal for long rendering tasks
Provides a web studio and command line interface

Use it for

Turning an EPUB ebook into a chaptered local audiobook
Cloning a voice from a short microphone sample
Generating audiobooks using commercial text-to-speech providers
Processing text formatting and stress for speech synthesis

Alternatives to Folivox

ebook2audiobook — Convert multiple ebook formats into audiobooks with voice cloning and 1158 languages.
Abogen — It creates audiobooks and voiceovers with custom voices and synchronized subtitles locally.
NovelHive AI — Role-aware narration with 86 voices and pay-per-book pricing.
Speechify — Converts any text to speech and creates podcasts from documents instantly.
Fish Audio — Provides studio-grade voice cloning and text-to-speech with emotion control.
Voicebox — Perform voice cloning and generation entirely on local hardware.
NaturalReader — It offers content-aware AI voices in over 90 languages with cross-device compatibility.
VoxCPM — Provides tokenizer-free multilingual speech with controllable voice creativity.
Audimind — It combines script editing, AI narration, smart alignment, and multi-track audio mixing in one workspace.
Superwhisper — Transcribes speech offline and online with custom AI modes and templates.
OpenLess — Keeps data local and allows the use of your own preferred ASR and LLM providers.
AudioEnhancerMAX — Local-first audio production with verified release evidence and built-in governance.

All Folivox alternatives