Mistral
MistralWave-2024
multimodal · Release May 15, 2024 · License n/a
This model processes both text and audio, enabling interactive voice-based conversations.
multimodalMistral
Updated today
Modalities
What goes in and what comes out.
Inputs
text, audio
Outputs
text, audio
Capabilities
speech recognition, dialogue management, text generation, audio response
Benchmarks snapshot
Structured JSON for reproducible comparisons.
{}Related on GenAIWiki
Same provider, tooling that cites the model, or prompts tuned for it.
Mistral
Mistral Large
Mistral Large supports up to 16k tokens with a response latency of 150ms, targeting enterprise-level applications and complex document understanding.
Mistral
Mixtral
Mixtral integrates large language processing with generative capabilities, managing up to 16,384 tokens while delivering high-quality content creation and response generation.