Open source TTS models Kokoro, Orpheus, and Piper are tested on symbols, abbreviations, and prosody with CER and MOS results.
Mistral launches Voxtral TTS, extending its model family into speech generation and enabling end-to-end voice workflows.
Small and fast: only 123M parameters. High-quality voice cloning: state-of-the-art performance in speaker similarity, intelligibility, and naturalness. Multi-lingual: support Chinese and English.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results