Hey — I’m trying to use mistralai/voxtral-mini-tts-2603 via OpenRouter and I’m confused about voice handling.
-
The OpenAI-style endpoint
/audio/speechaccepts avoiceparameter -
This works for
openai/gpt-4o-mini-tts -
But for Voxtral:
voicedoesn’t seem documented- behavior is inconsistent (ignored? default? unsupported?)
Questions:
- Does Voxtral support named voices at all via OpenRouter?
- If yes, is there a list of valid voices?
- Or is the intended usage reference audio (voice cloning) only?
- If cloning is supported, what is the correct request format on OpenRouter?
Right now it's unclear whether:
voiceis silently ignored- mapped internally
- or not supported at all
Would appreciate clarification or docs 🙏