metadata

language:
  - de
license: cc-by-nc-4.0
tags:
  - speech
  - text-to-speech
  - F5-TTS
datasets:
  - amphion/Emilia-Dataset
  - fsicoli/common_voice_19_0
library_name: f5_tts
base_model:
  - SWivid/F5-TTS

German Voice Cloning TTS Model using F5-TTS Architecture

A German Text-to-Speech system capable of cloning voices from a few seconds of reference audio, built on the F5-TTS architecture.

Model Details

Developed by: Johanna Reiml and team at KI-Servicezentrum, Hasso-Plattner-Institut (HPI)
Base Model: SWivid/F5-TTS
Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Key Features & Capabilities

Generates natural-sounding German speech from text
Clones voices using minimal reference audio (few seconds)
Suitable for audiobooks, voice assistants, and accessibility applications

Technical Specifications

Download checkpoints from the directories F5TTS_Base (vocos) or F5TTS_Base_bigvgan (bigvgan).

Datasets: Common Voice (Mozilla) and Emilia_DE
Process: Fine-tuned checkpoints of base F5-TTS model
Trained on Hardware: 8x NVIDIA H100

Contact

AI Service Center: kisz@hpi.de
Johanna Reiml: johanna@reiml.dev
Enes Suermeli: muhammed.suermeli@student.hpi.uni-potsdam.de
Kajo Kratzenstein: kajo.kratzenstein@student.hpi.de
Carlos Menke: carlos.menke@rwth-aachen.de

Acknowledgements

The authors acknowledge the financial support by the German Federal Ministry for Education and Research (BMBF) through the project «KI-Servicezentrum Berlin Brandenburg» (01IS22092).