A Russian speech synthesis model fine-tuned based on F5-TTS, supporting stress marking functionality with over 5000 hours of training.

OpenF5 TTS is an open-source text-to-speech model trained on the F5-TTS framework, supporting zero-shot voice cloning functionality, released under the Apache 2.0 license for commercial use.

Vietnamese text-to-speech model based on F5-TTS architecture, supporting neutral-style voice cloning

A compact version fine-tuned based on F5-TTS, trained with 150 hours of Vietnamese speech data, for research purposes only.

Audio ProcessingPytorchOther

A high-quality Arabic speech synthesis model fine-tuned based on F5-TTS, supporting diverse pronunciations and accents from different regions

Brazilian Portuguese text-to-speech model based on F5-TTS, supporting emotion tags and speaker feature control

F5-TTS German is a flow matching-based German text-to-speech model that supports high-quality speech synthesis.

Audio ProcessingSafetensorsMultiple Languages

Italian-specific text-to-speech model based on the F5-TTS architecture, fine-tuned with 73+ hours of Italian data

This is the Italian fine-tuned version of the F5-TTS model, trained on the facebook/multilingual_librispeech dataset, specializing in Italian text-to-speech tasks.

F5-TTS is a German speech synthesis model based on flow matching technology, focusing on generating smooth and faithful speech output.

F5-TTS is a fully non-autoregressive zero-shot text-to-speech model that supports high-quality speech synthesis.

F5-TTS is a flow matching-based voice synthesis model, focusing on fluent and faithful voice synthesis, especially suitable for scenarios like fairy tale narration.