Mistral
Voxtral 3 TTS
Mistral’s speech-synthesis Voxtral tier — expressive multilingual TTS in the Mistral stack.
Intelligence
90.2 #16
AAQI 90.0
Output Speed
165 t/s
ITL 6.1 ms/tok
Blended price (3:1)
$0.019 /1M
In $0.015/M · Out $0.03/M
Context
32K
≈ 80 A4 pages · max out 8,192
Quality Domain Radar
6-Axis Frontier Evaluation vs Category Average & Flagship
Voxtral 3 TTS
Claude Mythos Preview (#1)
Average (68)
Radar axes are approximated from category scores where direct benchmark measurements are missing — see Methodology.
Strengths & Trade-offs
Where it wins
- Top EU-language prosody
- One vendor for LLM + TTS + STT
- Competitive latency for conversational use
Trade-offs to watch
- English voices trail Eleven v3 on emotion
- Smaller voice library than ElevenLabs
- Closed weights
Killer Use Cases
European voice products
Native-quality fr/de/es/it synthesis.
Mistral-native agents
Voice loops inside the Mistral stack.
Accessibility readouts
Natural long-form reading for apps.
Developer Quickstart & API
Set
MISTRAL_API_KEY first — get an API keycurl https://api.mistral.ai/v1/chat/completions \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "voxtral-3-tts",
"messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.mistral.ai/v1",
api_key=os.environ["MISTRAL_API_KEY"],
)
resp = client.chat.completions.create(
model="voxtral-3-tts",
messages=[{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}],
)
print(resp.choices[0].message.content)const res = await fetch("https://api.mistral.ai/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.MISTRAL_API_KEY}`,
"content-type": "application/json",
},
body: JSON.stringify({
model: "voxtral-3-tts",
messages: [{ role: "user", content: "Refactor this function for O(n) time and explain the change." }],
}),
});
console.log((await res.json()).choices[0].message.content);Official Resources & Links
API deployment
Compare hosts & latency
Throughput, TTFT and cache pricing across Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock and Azure.
GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Scores by Source
Category Scores
Benchmark Results
Head-to-head Live Matchups
Live Specs & Architecture
Under the hood
Voxtral 3 TTS — Mistral speech synthesis
- Shares the Voxtral audio encoder lineage
- Expressive multilingual voices with style prompts
- Native EU-language coverage (fr/de/es/it/pt)
- Integrates with Mistral chat and agents
Release date
Oct 9, 2026
Architecture
Voxtral 3 TTS — Mistral speech synthesis
Parameters
Not disclosed
License
Proprietary
Context Window
32,000 tokens
Max Output
8,192 tokens
Modalities
text + audio
Cache Pricing
read $0.005 · write $0.019 /1M
Reasoning
—
Input Price
$0.015/M
Output Price
$0.03/M
Output Speed
165 t/s
Time to First Token
—
Data Updated
Oct 22, 2026
Estimated monthly bill
Estimated monthly spend
$0.00
Calculating savings vs GPT-4o...
Cite & embed
GitHub Markdown badge
Loading badge markdown...BibTeX
@misc{llmpodium2026voxtral3tts,
title = {Benchmark Analysis and Intelligence Evaluation of Voxtral 3 TTS},
author = {LLMPodium Research},
year = {2026},
url = {https://llmpodium.com/models/voxtral-3-tts}
}Embed Score Badge
Add a live Podium Score badge to your GitHub or Hugging Face README — it links back to the live ranking.
Preview
Markdown
Loading badge snippet...HTML
Loading badge snippet...More from Mistral
Alternative Models
Closest alternatives to Voxtral 3 TTS based on capabilities, pricing, and benchmark scores.