SauerkrautTTS-Preview-0.1 is a fine-tuned Text-to-Speech (TTS) model based on the powerful canopylabs/orpheus-3b-0.1-ft.

This preview model introduces four distinct German-speaking voices—Lena, Anna, Max, and Tom-crafted using original audio recordings captured with a Rhode Studio microphone and Mimic Studio, alongside carefully curated synthetic data. The high quality and careful curation of our overall dataset enable the model to produce clear and natural speech outputs, even from this initial release.

The synthetic audio data enriches the model, resulting in versatile and expressive voice capabilities.

For seamless inference and practical examples, check out our detailed instructions and ready-to-use scripts available on:

To achieve optimal results, we recommend using a lower temperature for clear and stable outputs. Higher temperatures will enhance dynamism and expressiveness but might introduce instability.

Example inference settings:

This model represents our first exploratory step into advanced German-language TTS. Expect significant improvements in upcoming versions, including:

Stay tuned for future releases and updates!

SauerkrautTTS-Preview-0.1 is openly available under the CC BY-NC 4.0 License, encouraging reuse, remixing, and improvements by the community.

We thank Unsloth for their invaluable training script, which we utilized in a lightly modified form for training this model. Also we are thankful for the German Ministry of Education and Research (BMBF) for funding our Project ARGUS, in which we developed SauerkrautTTS.