← All models
Mistral: Voxtral Mini TTS
mistralai/voxtral-mini-tts-2603speech
Compact TTS from Mistral: 30 voices, fast and economical.
Price
Context
4.1K
Released
Apr 19, 2026
Parameters
inputrequiredvoiceen_paul_sad · en_paul_neutral · en_paul_happy · en_paul_frustrated · en_paul_excited · en_paul_confident · en_paul_cheerful · en_paul_angry · gb_oliver_neutral · gb_oliver_sad · gb_oliver_excited · gb_oliver_curious · gb_oliver_confident · gb_oliver_cheerful · gb_oliver_angry · gb_jane_sarcasm · gb_jane_confused · gb_jane_shameful · gb_jane_sad · gb_jane_neutral · gb_jane_jealousy · gb_jane_frustrated · gb_jane_curious · gb_jane_confident · fr_marie_sad · fr_marie_neutral · fr_marie_happy · fr_marie_excited · fr_marie_curious · fr_marie_angryVoice sample
0:00 / 0:00
How to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.audio.speech.create(
model="mistralai/voxtral-mini-tts-2603",
voice="en_paul_sad", # en_paul_sad, en_paul_neutral, en_paul_happy, en_paul_frustrated, en_paul_excited...
input="Привет! Это Mixen AI.",
)
resp.stream_to_file("speech.mp3")
