All models
xAI
Grok Voice TTS 1.0
Speech with pauses and emphasis marked up right in the text
This model is not in the catalog right now.
See available modelsAbout the model
Grok Voice TTS 1.0 reads text in five voices, Eve, Ara, Rex, Sal and Leo, and detects on its own which language it is written in. Its distinctive feature: markup can be placed right in the text, for pauses, emphasis, pitch and tempo, and the model will act on it, with no separate markup format required. According to the publisher, it speaks more than 20 languages and accepts up to 15,000 characters per request.
Strengths
- Five voices: Eve, Ara, Rex, Sal, Leo
- Pause, emphasis, pitch and tempo as tags in the text
- Detects the language of the text on its own
- According to the publisher: more than 20 languages, up to 15,000 characters per request
Where to use it
- Voice-overs with precise pause placement
- Multilingual recordings without manual switching
- Long texts in a single request