Skip to content
ArenaPlatform

Voxtral Mini 2507

deepinfra/voxtral-mini-2507

Mistral's Voxtral Mini (July 2025), a 3B speech-understanding model built on Ministral 3B: transcription with automatic language detection, translation and audio Q&A for long recordings. Mistral's newer Voxtral Transcribe 2 release includes Voxtral Mini 4B Realtime.

Get API KeyRead the Docs
API
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -F 'model=deepinfra/voxtral-mini-2507' \
  -F 'file=@recording.wav'
Read docs
Input Price
$0.0009 / minute
Output Price
—
Input
Audio
Output
Text

Capabilities

Explore what Voxtral Mini 2507 supports, then use the API section for a request tailored to this model.

BatchWord timestampsSegment timestamps

Languages

Multilingual

Model Information

Provider
DeepInfra
Product
Speech-to-Text
Release Date
Jul 15, 2025
Data Policy
Not specified
Region
US
Input
Audio
Output
Text
Provider Documentation

Playground

Try Voxtral Mini 2507 by DeepInfra. Requests use the selected workspace’s credits and API pricing.

Voxtral Mini 2507Credits —
Voxtral Mini 2507
Attach an audio file to turn speech into text.
Sign in to run a requestAPI reference

Providers

Compare available endpoints, pricing, and context limits for Voxtral Mini 2507.

ProviderContextOutputInput PriceOutput PriceEndpoint
DeepInfraNot specifiedText$0.0009 / minute—
deepinfra/voxtral-mini-2507:deepinfra

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max bytesNot specified
Max seconds3600
Formatsmp3, flac

Provider Notes

These are all currently active automatic-speech-recognition entries in DeepInfra's model catalog. AudioLab uses each model's native inference endpoint and accepts the documented MP3 or FLAC byte upload. Translation is available only on the two Whisper models; the Nemotron and Voxtral entries reject it. Despite its upstream name, Nemotron 3.5 ASR Streaming is currently exposed through DeepInfra's request/response inference API here, not AudioLab's live WebSocket route.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -F 'model=deepinfra/voxtral-mini-2507' \
  -F 'file=@recording.wav'
Read docs
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modeldeepinfra/voxtral-mini-2507 — Required model identifier.
chunk_length_sView Accepted Values
chunk_level (segment or word)View Accepted Values
service_tier (default, priority, or flex)View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max bytesNot specified
Max seconds3600
Formatsmp3, flac

Similar Models

Explore more speech-to-text and compare their capabilities.

ModelContextInput PriceOutput Price
Nemotron 3.5 ASR StreamingDeepInfraNot specified$0.0002 / minute—
qwen3-asr-0.6bDeepInfraNot specified$0.0002 / minute—
qwen3-asr-1.7bDeepInfraNot specified$0.0004 / minute—
Voxtral Small 2507DeepInfraNot specified$0.0026 / minute—
Whisper Large v3 TurboDeepInfraNot specified$0.0002 / minute—
Whisper Large v3DeepInfraNot specified$0.0004 / minute—
View All Speech-to-Text