estebanstifli/LocalText2Voice

Free open-source AI desktop app for audiobooks, podcasts, documentaries, films and animated videos with local models, cloud APIs and editable storyboards.

What it solves

LocalText2Voice is a desktop application designed for long-form AI audio and video production. It solves the difficulty of turning large volumes of text—such as books, lessons, and scripts—into high-quality audiobooks, podcasts, documentaries, and animated videos without requiring expensive subscriptions or relying solely on cloud-based services.

How it works

The app provides a complete production pipeline: users import text (TXT, MD, DOCX, or EPUB), apply optional markup for voice and pacing, and generate narration using a choice of local or cloud TTS engines. The workflow includes a review loop where generated audio is compared against the original text using Faster Whisper. For video production, the "Video Storyboard" feature analyzes the narration to identify scenes and characters, allowing users to generate or import visuals and render a final MP4 video.

Who it’s for

It is built for creators of long-form content, including authors producing audiobooks, educators creating illustrated lessons, and filmmakers or podcasters who need a privacy-first, offline-capable tool for narration and video assembly.

Highlights

  • Hybrid TTS Architecture: Supports a wide array of local engines (Piper, Kokoro, Chatterbox, Qwen3 TTS, OmniVoice, F5-TTS) and cloud APIs (OpenAI, ElevenLabs, Gemini, Azure).
  • Video Storyboard: A beta tool that transforms narration into a visual timeline with scene analysis, character continuity, and batch video generation.
  • Privacy-First: Local engines keep all text and audio data on the user's computer.
  • Long-Form Optimized: Specifically designed to handle chapters and large documents, including support for M4B audiobook exports.
  • Audio Mixing: Includes tools for adding background music with ducking and fades for podcast-ready results.
  • MCP Integration: Automates the Video Storyboard workflow via Model Context Protocol (MCP) tools.

Related

  • Project
    jamiepine/voicebox

    An open-source, local-first AI voice studio for voice cloning, text-to-speech, and system-wide dictation, featuring integration with MCP-aware AI agents.

  • Project
    naqashafzal/AI-Content-Studio

    AI Content Studio is an open‑source platform that automates the whole video‑creation workflow. A supervisory set of AI agents researches a topic, writes and QA‑checks a script, then a multimodal pipeline (Whisper transcription, OpenCV scene analysis, FFmpeg processing) produces a fully‑styled, loudness‑normalized video with captions, B‑roll and branding. It supports style‑cloning from reference clips, Urdu TTS, and 24/7 auto‑pilot campaigns, and runs via a FastAPI backend + Next.js UI.

  • Project
    tover0314-w/opentypeless

    An open-source AI voice input tool for macOS, Windows, and Linux that provides app-aware dictation, voice Q&A, and text rewriting.

  • Project
    Beingpax/VoiceInk

    VoiceInk is a macOS‑only, offline speech‑to‑text app that uses local Whisper‑based models (via whisper.cpp and transcribe‑cpp‑swift) to provide near‑instant, privacy‑preserving transcription, context‑aware modes, custom dictionaries, global shortcuts, and a built‑in AI assistant. It’s open‑source under GPL‑v3, installable via Homebrew or from source, with optional paid licensing for updates and support.

  • Project
    akshayaggarwal99/jarvis-ai-assistant

    An open-source voice dictation tool that converts speech to text anywhere on your system, supporting local transcription and LLM post-processing for privacy and speed.