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.

Mistral's new speech model can run on a smartwatch or a smartphone.

For as much excitement as there is around AI at the moment, most of the practical applications discussed in the public are around Chat GPT. Chat GPT is a powerful tool - don’t get me wrong, but it is ...

The Paris-based Mistral AI SAS today announced the release of Voxtral TTS, its first text-to-speech artificial intelligence ...

Mistral AI launches Voxtral TTS, an open-weight enterprise voice model that runs on a smartphone and challenges ElevenLabs in the fast-growing voice AI market.

Is the text-to-speech world on the brink of a revolution? With the release of Qwen3-TTS, some are calling it the “ElevenLabs killer,” and for good reason. In this guide, Prompt Engineering explains ...