thorstenMueller/Thorsten-Voice

Thorsten-Voice: A free to use, offline working, high quality german TTS voice should be available for every project without any license struggling.

What it solves

This project provides high-quality, open-source German voice datasets to enable the creation of free, offline, and license-free text-to-speech (TTS) systems. It aims to remove barriers for developers who need a natural-sounding German voice for their applications without relying on proprietary or paid services.

How it works

Thorsten Müller recorded thousands of phrases across different styles and qualities. These recordings are organized into several datasets (Neutral, Emotional, and Hessisch dialect) and are available in formats compatible with standard ML structures (like LJSpeech). These datasets are then used by AI/ML researchers and projects—such as Coqui AI, Piper TTS, and Home Assistant—to train neural text-to-speech models.

Who it’s for

  • AI/ML Researchers: Those training new German TTS models.
  • Developers: People building offline German voice assistants or accessibility tools.
  • Smart Home Enthusiasts: Users integrating high-quality German voices into platforms like Home Assistant.

Highlights

  • Diverse Datasets: Includes neutral speech, emotional recordings (8 different emotions), and the Hessisch dialect.
  • High Fidelity: Offers a full 44kHz samplerate dataset on Hugging Face.
  • Broad Integration: Already utilized by major open-source TTS engines like Piper and Coqui AI.
  • Permissive Licensing: Released under CC0 for unrestricted use in projects and products.

Related

  • Project
    rsxdalv/TTS-WebUI

    A unified web interface and manager for a wide variety of open-source text-to-speech, audio generation, and audio conversion AI models.

  • Project
    OpenMOSS/MOSS-TTS

    A family of open-source speech and sound generation models providing high-fidelity TTS, multi-speaker dialogue, voice design, real-time streaming, and sound effect generation.

  • Project
    2noise/ChatTTS

    ChatTTS is a generative text-to-speech model optimized for conversational dialogue, providing natural, expressive speech with control over laughter and pauses.

  • Project
    datascale-ai/opentalking

    An open-source orchestration framework for real-time digital-human conversations, integrating LLMs, TTS, STT, and video rendering via WebRTC.

  • Project
    snakers4/silero-models

    A collection of fast, end-to-end text-to-speech models supporting a wide variety of languages, designed for efficient execution on CPU and GPU.