Voxtral 4B TTS 2603
Mistral's Voxtral 4B TTS 2603 is an open-source, text-to-speech model that excels at producing realistic, expressive speech with natural prosody and emotional range across 9 major languages. It is particularly well-suited for enterprise-grade applications, such as customer support and call center infrastructure, due to its very low latency and production-ready performance.
Input
Output
Context
-
Max Output
-
Parameters
4B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Estimated GPU requirements for Voxtral 4B TTS 2603
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by Mistral
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Voxtral 4B TTS 2603
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Mistral has not published a context window for Voxtral 4B TTS 2603, so the catalog shows it as not available rather than estimating one.
Yes. Voxtral 4B TTS 2603 is an open-weight model released under the Cc by nc 4.0 license, so the weights can be downloaded and self-hosted within that license's terms.
Voxtral 4B TTS 2603 accepts Text and produces Audio. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Voxtral 4B TTS 2603 is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; Voxtral 4B TTS 2603 is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
About 4.3 GB at INT8 for the weights and a default context, from the catalog's 4B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Aug 28, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.