Tasks and inputs
Voxtral Mini Transcribe 2 is listed for Automatic speech recognition. It accepts audio and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 7, 2026
Voxtral Mini Transcribe 2 is Mistral's audio-input model for transcription workloads.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Voxtral Mini Transcribe 2 is Mistral's audio-input model for transcription workloads.
Transcription turns a recording into text. It does not generate a spoken reply or automatically provide a conversational voice agent. Use a recording-based transcription workflow for uploaded meetings, interviews and support calls; use a documented realtime interface when partial results during a live stream are essential.
Store the file identifier, language settings and requested output options with the transcript. When timestamps or speaker-related output are required, confirm those features for the exact API version instead of assuming every audio model exposes the same response schema.
Include accents, background noise, interruptions and overlapping speakers from your actual recordings. Score names, amounts and technical vocabulary separately from ordinary conversational text. A transcript can have a low overall error rate while getting the customer name or requested action wrong.
Compare the final output with a human reference and keep corrections tied to timestamps. If you add summarization, verify it as a second stage: a fluent summary can hide an upstream transcription mistake.
Audio billing uses the documented audio schedule, so an ordinary input/output text-token rate is left unset here. Check the current service price, upload limits and retry behavior before estimating a backlog. For a local streaming alternative, inspect Voxtral Mini Realtime, including its different runtime and operational requirements.
Publisher source 1 Deployment limits and commercial terms belong to the selected checkpoint or API route.
Compare the model on the work you need to complete.
Voxtral Mini Transcribe 2 is listed for Automatic speech recognition. It accepts audio and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Gemini 3.5 Transcribe Live from Google: Speech transcription model for accurate audio-to-text and captioning workflows.
xAI
Grok Voice STT 1.0 from xAI: Grok Voice STT 1.0 is xAI's speech-to-text model. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.
OpenAI
GPT Realtime Whisper from OpenAI: Streaming speech-to-text model for low-latency transcript deltas from live audio.
openai
openai/whisper-large-v3-turbo is a source-linked Hugging Face repository assigned to Automatic speech recognition. Its recorded task interface accepts audio and produces text.
OpenAI
Whisper 3 Large from OpenAI: Open Whisper checkpoint for robust multilingual transcription and captioning.
OpenAI
Whisper Large v3 Turbo from OpenAI: Speech transcription model for accurate audio-to-text and captioning workflows.