Voxtral TTS 3
Voxtral TTS 3 audio model
Use Voxtral TTS 3 in Vizify with its current audio limits visible.
Voxtral TTS 3 runs as Speech in the current public catalog. Vizify inspects the route before every job and passes only the parameters listed here.
Available in Vizify Speech Voice selection
Explore your idea with AI before generating.
Sign-in and access checks apply in Vizify.
Verified catalog facts
What Vizify exposes for this model family.
These facts are generated from the current public catalog, not copied from provider marketing.
Text
Audio
Audio generation
Reviewed 2026-11-01
Where this model fits.
Prepare a Speech request that matches the Voxtral TTS 3 route
Inspect the current parameters before running Voxtral TTS 3
Receive one completed asynchronous Speech artifact from Voxtral TTS 3
What not to assume.
Vizify passes only the parameters listed on this page; anything else is dropped before Voxtral TTS 3 runs.
Voxtral TTS 3 takes no reference upload; every request on this route starts from text.
Availability and parameters for Voxtral TTS 3 were checked against Vizify's generation catalog on 2026-11-01. That check does not establish market ranking, external pricing, licensing, or benchmark leadership.
Mode first
Voxtral TTS 3 is listed in Vizify’s public catalog as Speech, and that fact decides which tools can reach it: each tool prepares its brief for one mode, and Vizify will not route a request to a model published under another.
What Vizify passes
Before execution Vizify reads the current parameter list for Voxtral TTS 3 and sends only what it finds there: Voice selection. This route generates from text alone: it accepts no reference audio and no reference image. Anything this route does not expose is left out rather than quietly replaced with something close.
Evidence boundary
Availability, mode and parameters for Voxtral TTS 3 were checked against Vizify’s generation catalog on 2026-11-01. Nothing here establishes market ranking, external pricing, licensing terms or benchmark leadership, and the entry can change between reviews.
FAQ
Questions about Voxtral TTS 3 in Vizify
Is Voxtral TTS 3 available in Vizify?
Yes. Voxtral TTS 3 is in the current public audio catalog and runs as Speech. Availability is read from that catalog at request time, not promised by this page.
Which audio mode does Voxtral TTS 3 run?
Speech. Every compatible tool on this page builds its request for that mode, so your brief arrives in the shape Voxtral TTS 3 expects.
Which Voxtral TTS 3 parameters does Vizify pass?
The inspected parameter set is: Voice selection. Values outside that list are not sent, and Vizify never swaps in an approximation for an option this route does not expose.
Can I upload reference audio to Voxtral TTS 3?
Voxtral TTS 3 takes no reference upload; every request on this route starts from text. Reference uploads need a free Vizify account and reach only a route that lists support for them.
What does Voxtral TTS 3 not do?
Voxtral TTS 3 returns one asynchronous Speech artifact per request: no separated stems, no exact duration, no licensing clearance, and no ranking against another model.
Where do I start with Voxtral TTS 3?
Open one of the compatible tools listed here and write the brief there. Vizify inspects Voxtral TTS 3 at run time, prepares a Speech request, and follows the job to completion or failure.