dectalk/dectalk

Modern builds for the 90s/00s DECtalk text-to-speech application.

What it solves

DECtalk is a text-to-speech (TTS) system that converts written text into spoken audio. It provides a source code archive of a classic speech synthesis engine, allowing users to run it on modern platforms including Linux, Windows, MacOS, and iOS.

How it works

The project preserves and compiles the original source code shared by its developers. It uses a build system that supports multiple architectures (i386, x86_64, aarch64) and can be deployed as a native binary or run in a web browser via WebAssembly.

Who it’s for

Developers and enthusiasts interested in classic speech synthesis, as well as users who looking to integrate this specific TTS engine into their applications or run it on modern hardware.

Highlights

  • Support for multiple operating systems including Linux, Windows, MacOS, and iOS.
  • Availability as a WebAssembly build for browser-based use.
  • Comprehensive build instructions for various environments, including Docker support for Linux.
  • Preservation of original source code from the original developers.

Related

  • Project
    VOICEVOX/voicevox_engine

    VOICEVOX Engine is an HTTP server that provides Japanese text‑to‑speech (and singing) using the VOICEVOX neural TTS core. It offers endpoints for normal synthesis, streaming, voice‑style morphing, custom pronunciation dictionaries, presets, and cancellable synthesis. The engine can run on CPU or GPU, is packaged as Docker images, and is meant for developers integrating Japanese TTS into applications.

  • Project
    Xerophayze/TTS-Story

    TTS‑Story is a web UI for multi‑voice audiobook creation. It lets you tag speakers, design or clone voices (via Google Gemini Cloud or many local models), run a queue of TTS jobs, review audio in‑app, and export MP3/M4B. Supports 20+ engines, GPU/CPU isolation, bulk voice casting, directed‑narration, and optional LLM text‑prep.

  • Project
    espeak-ng/espeak-ng

    A compact, open-source text-to-speech synthesizer using formant synthesis to support over 100 languages with a very small memory footprint.

  • Project
    nateshmbhat/pyttsx3

    A Python library for offline text-to-speech conversion that utilizes native system engines to generate voice output without an internet connection.

  • Project
    dbccccccc/ttsfm

    An OpenAI-compatible text-to-speech API service and Python SDK that converts text to natural speech using the openai.fm backend.