Text-to-Speech Models
AI-Corporate supports text-to-speech models that convert text to audio.
Current Catalog
| Provider | Model | Note |
|---|---|---|
| OpenAI | GPT-4o mini TTS | Natural speech with good control over tone and style. |
| Gemini 3.1 Flash TTS Preview | Gemini speech model with precise control over style, pace and tone. | |
| European AI | Voxtral Mini TTS | European text-to-speech based on Mistral Voxtral Mini. |
Claude has no text-to-speech model in the catalog. If Claude is enabled, speech models still depend on the other configured providers.
Voices and Languages
Available voices differ by provider. AI-Corporate only shows voices that match the selected language, or voices that can be used across languages.
System Prompt
For text to audio, the system prompt can steer pronunciation and style, for example natural Dutch, English pronunciation for product names, or French pronunciation for Claude.