Primary use stated or inferred cautiously from official documentation.
M
MISTRAL AI / voxtral-mini-tts-2603
Voxtral TTS
Multilingual text-to-speech model with streaming and zero-shot cloning from a voice reference.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | voxtral-mini-tts-2603 |
|---|---|
| Model type | Voice and audio |
| Access model | API and open weights |
| License | CC BY-NC 4.0 |
| Deployment | API or local with license restrictions |
| Release | 23 MAR 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Reference audio |
| Exit | Audio |
| Context window | Text and voice reference |
| maximum output | Streaming audio |
| Reasoning | Not applicable or not published |
| Published tools | |
| Structured Outings | Not applicable or not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Downloadable weights |
| Verified platforms | Mistral API |
Narration, voice prototyping, and multilingual synthesis.
The license is non-commercial; review consent and voice rights before cloning.
03 / CAPABILITIES
What it can do
Orientation
Narration, voice prototyping, and multilingual synthesis.
Context
Text and voice reference · Streaming audio
Tools and integration
Not published
Access
Mistral API and weights
Input modalities
TextReference audio
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source: the billing unit depends on the model type and access channel.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Evaluaciones Voxtral TTS | ~90 ms | Published time to first audio | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Voxtral TTS
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
Voxtral TTS: what a team should validate before replacing a synthetic voice in production
Mistral AI documents Voxtral TTS as a speech-generation service with streaming and several output formats. Before replacing a provider or model in calls, notifications, or published content, a team should verify not only audible quality, but also technical, operational, and data-contract compatibility through a regression suite using its own scripts.
22 Sep 2026 ↗
Synthetic Voices in Production: How to Demonstrate Consent, Control Likeness, and Remove a Voice Without Losing Traceability
Using a synthetic voice responsibly requires more than a checkbox or a convincing demo. This guide proposes an operating system for linking each audio asset to a specific authorization, controlling the risk of resemblance to identifiable people, disclosing its nature where appropriate, and removing assets when the terms of use change.
22 Sep 2026 ↗07 / SOURCES