LLM EU
Menüü

Voxtral Small 24B

Mistral AI · Pakkujad EU

Ainult kataloogis Avatud kaalud Euroopa pakkuja

Suveräänsus ja majutamine

Ainult kataloogis

See mudel on loetletud viitamiseks. Seda ei majutata veel LLM EU-s ega teeninda seda siin ükski esimese osapoole lõpp-punkt. Päringud suunatakse otse pakkujale, pakkuja enda tingimustel.

Kokkuvõte

Voxtral Small is an Apache-2.0 audio-input model that transcribes and reasons over speech, with a 32k-token context that the vendor maps to roughly 30 minutes of audio for transcription and 40 minutes for understanding. It also works as a text model and supports automatic source-language detection. The card lists English, Spanish, French, Portuguese, Hindi, German, Dutch and Italian as its target languages.

Tehnilised andmed

Pakkuja
Mistral AI (FR)
Konteksti aken
33k
Parameetrid
24.26B
Modaalsused
audio, text
Litsents
apache-2.0 · licence
Avatud kaalud
yes
Avaldamiskuupäev
01. juuli 2025
Ülesanded
translation, summarization, multilingual-support, customer-support

Keeled

Tugev: en, es, fr, pt, de, nl, it

Piisav: hi

Keeled

Tugev

  • en
  • es
  • fr
  • pt
  • de
  • nl
  • it

Piisav

  • hi

Verifitseerimata: pakkuja ei ole seda väidet dokumenteerinud. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Millal kasutada

Tugevused

  • open-weight speech transcription and audio question answering
  • automatic source-language detection
  • also usable as a text model
  • Apache-2.0 licence

Piirangud

  • 32k-token window limits audio to about 30 to 40 minutes per request
  • language coverage is narrower than Whisper’s
  • no evaluation has been run by LLM EU