Voxtral Mini 4B Realtime Arabic
Voxtral Mini 4B Realtime Arabic is available now for vision with open-source; evaluate it while provider pricing coverage matures.
- Family
- Voxtral
- Released
- 2026-10-09
- Parameters
- 4.4B
- Specialization
- speech-recognition
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
No tracked provider token pricing is available yet.
About
Voxtral Mini 4B Realtime Arabic is Mistral AI's open-weight streaming speech-to-text model for Modern Standard Arabic and Arabic dialects (Maghrebi, Gulf, Nile Valley, Levantine and others), built to handle code-switching between languages within one conversation. It is fine-tuned from Voxtral Mini 4B Realtime 2602, has about 4.4B parameters in BF16, and processes 16 kHz audio through a causal audio encoder and language decoder so text is produced as audio arrives, with a configurable transcription delay. Mistral reports an average 8.82% character error rate across seven Arabic benchmarks at a 480 ms delay.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
Voxtral Mini 4B Realtime Arabicmistralai/Voxtral-Mini-4B-Realtime-ArabicNo tracked provider token pricing is available yet.