AI TOOLS RADAR
Explorar
Todos os modelos / MISTRALAI
mistralai logo
mistralai

Mistral: Voxtral Small 24B 2507 STT

Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.

Ver fonte no OpenRouter Hugging Face
Visão geral

Especificações do modelo

Context
Not provided
Saída máxima
Not provided
Arquitetura
audio->transcription
Tokenizador
Mistral
Limite de conhecimento
Not provided
Moderado
Não
Recursos e modalidades

Input → Output

Input
audio
Output
transcription
API

Parâmetros de API compatíveis

frequency_penaltymax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstoptemperaturetop_ktop_p
Provedores disponíveis

1 Provedor

DeepInfra

bf16
Context
Not provided
Saída máxima
Not provided
Input
$50.00
Output
Free
Leitura de cache
Not provided
Gravação de cache
Not provided
mistralai

models

Todos os modelos
mistralai logomistralai

Mistral: Voxtral Mini 3B 2507

Voxtral Mini 3B 2507 is a speech and audio understanding model from Mistral AI. It is suited for transcription, translation, and compact audio processing workloads.

Context
Not provided
Input
audio
Output
transcription
Input: $16.67Output: Freeper 1M tokens
Ver detalhes do modelo →