Voxtral Mini Transcribe Realtime
Mistral AIdocs.mistral.ai/models/voxtral-mini-transcribe-r
An efficient audio input model, pre-trained and optimized for live transcription purposes.
Updated 2 h ago · first seen 11 Sept 2026
model_01M2943ZSQ5QBXGBWEYW6MRZMM
- License
- Apache 2.0
- T1 · 2 h ago
Specification
- Version
- 26.02
Source:Mistral AI docsT1observed 2 h agohigh
- Openness
- open-weights
Source:Mistral AI docsT1observed 2 h agohigh
- License
- Apache 2.0
Source:Mistral AI docsT1observed 2 h agohigh
- API alias
- voxtral-mini-transcribe-realtime-latest
Source:Mistral AI docsT1observed 2 h agohigh
- Official page
Source:Mistral AI docsT1observed 2 h agohigh
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
6
Source tiers
T16
Freshest observation
2 h ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
No capability flags have been observed from a source yet — we do not infer them.
No structured attributes yet.
No benchmark results recorded
Current prices
No current prices recorded
Price history
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Versionversion1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 26.02 | → current | current | Mistral AI docsT1 | high | deterministic |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| open-weights | → current | current | Mistral AI docsT1 | high | deterministic |
Licenselicense1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Apache 2.0 | → current | current | Mistral AI docsT1 | high | deterministic |
API aliasapi_alias1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| voxtral-mini-transcribe-realtime-latest | → current | current | Mistral AI docsT1 | high | deterministic |
Official pageofficial_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-26-02 | → current | current | Mistral AI docsT1 | high | deterministic |
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| An efficient audio input model, pre-trained and optimized for live transcription purposes. | → current | current | Mistral AI docsT1 | high | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New model: Voxtral Mini Transcribe Realtime (Mistral AI)
mistral
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Mistral AI docs | docs.mistral.ai/models | model_docs | T1· Official | 1 h ago | 1 |
| Mistral AI docs | docs.mistral.ai/models/voxtral-mini-transcribe-realtime-26-02 | model_page | T1· Official | 2 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.