Mistral AIAudio modelActive
Voxtral Mini Transcribe Realtime
PopularityRank 602 of 876
18out of 100same as last month
Summary
Mistral describes Voxtral Mini Transcribe Realtime as an efficient model pretrained and optimized for live transcription only. Its model page lists version v26.02 as generally available under Apache 2.0. Mistral exposes it through the API and for local execution.
Voxtral Mini Transcribe Realtime v26.02 is generally available under Apache 2.0 and can run through the API or locally. Its exact API model ID is voxtral-mini-transcribe-realtime-2602. Voxtral Mini Transcribe 2 remains the separate path for files analyzed later; the realtime variant stays specialized for transcription rather than general audio chat.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 101 published benchmark results
Page 1 of 9
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
VoiceCodeBench: CTEM (Show measurement, test conditions, and source)
- Source value
- 83.333
- Score
- 83.333
- Metric
- canonical token/entity match
- Unit
- %
- Benchmark version
- 1
- Category
- general
- Task
- ctem
- Task label
- CTEM
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-11-06
- Methodology
- Source model ID: mistral/voxtral-mini-transcribe-realtime-2602. Source model name: Voxtral Mini Transcribe Realtime. Provider reported by source: Mistral. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-24. Latency in seconds: 15.376. Standard error: 0. Cost per task in USD: 0.006704. Source ID: vals-ai. Evidence capture ID: vals-voice-code-bench-2026-11-06-7753d162bfe3. Source payload hash: 7753d162bfe3fa3470d586da3917bf8ddd96f14e10f9aa8f03dd517b8d5f003b. Parser version: vals-astro-v4. Imported at: 2026-11-06. Source cohort: vals-voice-code-bench:1:ctem
VoiceCodeBench: Overall (Show measurement, test conditions, and source)
- Source value
- 46
- Score
- 46
- Metric
- task success rate
- Unit
- %
- Benchmark version
- 1
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-11-06
- Methodology
- Source model ID: mistral/voxtral-mini-transcribe-realtime-2602. Source model name: Voxtral Mini Transcribe Realtime. Provider reported by source: Mistral. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-24. Latency in seconds: 15.376. Standard error: 0. Cost per task in USD: 0.006704. Source ID: vals-ai. Evidence capture ID: vals-voice-code-bench-2026-11-06-7753d162bfe3. Source payload hash: 7753d162bfe3fa3470d586da3917bf8ddd96f14e10f9aa8f03dd517b8d5f003b. Parser version: vals-astro-v4. Imported at: 2026-11-06. Source cohort: vals-voice-code-bench:1:overall
Artificial Analysis AA-WER Streaming (final transcription) (Show measurement, test conditions, and source)
- Source value
- 5.2393
- Score
- 5.2393
- Metric
- word error rate (WER)
- Unit
- %
- Benchmark version
- AA-WER v2.2 streaming
- Category
- audio
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Independent evaluation. Direct API streaming evaluation; final-transcription WER across AA-AgentTalk (50%), VoxPopuli (25%), and Earnings22 (25%), about eight hours total. WER is duration-weighted within dataset; Earnings22 chunking is reassembled at parent-call level. AA-WER v2.2 streaming protocol.
Coval pooled corpus-level STT word error rate (Show measurement, test conditions, and source)
- Source value
- 5.3588643092655595
- Score
- 5.3588643092655595
- Metric
- Pooled corpus-level speech-recognition word error rate, Coval pooled_value
- Unit
- %
- Benchmark version
- Coval rolling 30-day window, re-measured daily; route last measured 2026-10-16
- Category
- audio
- Direction
- Lower is better
- Sample
- 25882
- Source type
- official-leaderboard
- Evaluator
- Coval
- Status
- superseded
- Retrieved at
- 2026-10-16
- Methodology
- Official benchmark leaderboard. Coval endpoint key mistral/voxtral-mini-transcribe-realtime-2602, exact Mistral API model ID voxtral-mini-transcribe-realtime-2602, hosted by Mistral. The route names the 2602 realtime checkpoint, not a family-level Voxtral result. Rolling 30-day window, re-measured daily.
- Context
- This is Coval's pooled corpus-level STT WER, not the separate per-clip mean_value or a rounded leaderboard headline. Pooled WER and mean per-clip WER are different aggregations and should not be compared as the same score. The WER row's sample_count is used, not another metric's count or a roster total. The result describes Coval's hosted 30-day endpoint cohort, not local or native performance.
Pipecat STT Benchmark semantic WER mean (Show measurement, test conditions, and source)
- Source value
- 4.49
- Score
- 4.49
- Metric
- Arithmetic mean semantic word error rate across successfully transcribed samples
- Unit
- %
- Benchmark version
- Pipecat STT Benchmark at commit 94f567299a21f8d617039bc69f137a131f5dedd5, September 2026 semantic-WER judge update
- Category
- audio
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Pipecat STT Benchmark
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. The pinned results table reports semantic WER over 1000 attempted samples from pipecat-ai/smart-turn-data-v3.1-train. WER Mean is the average across samples with a returned transcript; the table reports 99.3% transcript success, but does not give the exact number of WER-scored samples. Semantic scoring by Claude Sonnet 5.5 ignores punctuation, contractions, fillers, and equivalent phrasings. The source does not document a language distribution; its dataset preview shows English transcripts.
- Context
- No exact WER-scored N or model-specific confidence interval is published. The 1000 figure is attempted samples, not the WER denominator. The README says differences below about 0.25 percentage points are within the 95% bootstrap interval among the most accurate services, so do not rank close scores.
Pipecat STT Benchmark semantic pooled WER (Show measurement, test conditions, and source)
- Source value
- 5.11
- Score
- 5.11
- Metric
- Pooled semantic word error rate, total judged errors divided by total reference words
- Unit
- %
- Benchmark version
- Pipecat STT Benchmark at commit 94f567299a21f8d617039bc69f137a131f5dedd5, September 2026 semantic-WER judge update
- Category
- audio
- Direction
- Lower is better
- Source type
- independent-evaluator
- Evaluator
- Pipecat STT Benchmark
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. The pinned results table reports semantic WER over 1000 attempted samples from pipecat-ai/smart-turn-data-v3.1-train. Pooled WER is total judged semantic word errors divided by total reference words, among samples with a returned transcript; the table reports 99.3% transcript success but not the exact scored N. Semantic scoring by Claude Sonnet 5.5 ignores punctuation, contractions, fillers, and equivalent phrasings. The source does not document a language distribution; its dataset preview shows English transcripts.
- Context
- No exact WER-scored N or model-specific confidence interval is published. The 1000 figure is attempted samples, not the WER denominator. The README says differences below about 0.25 percentage points are within the 95% bootstrap interval among the most accurate services, so do not rank close scores.
A5Sv2 ASR benchmark, Mega-ASR fixed robustness selection (Show measurement, test conditions, and source)
- Source value
- 32.546769
- Score
- 32.546769
- Metric
- word error rate (WER)
- Unit
- %
- Benchmark version
- A5Sv2 pinned release commit 64284911a02b38ce07e1d184c56b9c1335f20b57
- Category
- audio
- Direction
- Lower is better
- Sample
- 32928
- Source type
- independent-evaluator
- Evaluator
- AirCaps A5Sv2 ASR benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Exact Mistral API model ID voxtral-mini-transcribe-realtime-2602; native causal streaming with 480 ms transcription delay, real-time paced 560 ms PCM chunks, final transcripts only. One saved run per system and corpus, frozen word-onset v2 references. Mega-ASR uses a fixed sample of 1,250 utterances from Voices-in-the-Wild-2M training splits, not its standard test set.
- Context
- This is a different dataset and protocol from the existing Oct 16 Voxtral results. The benchmark reports one saved run, without repeated trials or a confidence interval. The API model ID is not tied to an immutable serving build. AirCaps says its own A5Sv2 checkpoint was not optimized on the exact Mega-ASR items, but cannot determine whether third-party systems saw overlapping upstream data.
A5Sv2 ASR benchmark, AMI scenario-only evaluation meetings (Show measurement, test conditions, and source)
- Source value
- 48.712342
- Score
- 48.712342
- Metric
- word error rate (WER)
- Unit
- %
- Benchmark version
- A5Sv2 pinned release commit 64284911a02b38ce07e1d184c56b9c1335f20b57
- Category
- audio
- Direction
- Lower is better
- Sample
- 32928
- Source type
- independent-evaluator
- Evaluator
- AirCaps A5Sv2 ASR benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Exact Mistral API model ID voxtral-mini-transcribe-realtime-2602; native causal streaming with 480 ms transcription delay, real-time paced 560 ms PCM chunks, final transcripts only. One saved run per system and corpus, frozen word-onset v2 references. AMI uses seven scenario-only unseen-evaluation meetings and Array1-01 audio.
- Context
- This is a different dataset and protocol from the existing Oct 16 Voxtral results. The benchmark reports one saved run, without repeated trials or a confidence interval. The API model ID is not tied to an immutable serving build. AirCaps says its own A5Sv2 checkpoint was not optimized on the exact Mega-ASR items, but cannot determine whether third-party systems saw overlapping upstream data.
A5Sv2 ASR benchmark, DiPCo evaluation and development meetings (Show measurement, test conditions, and source)
- Source value
- 75.521839
- Score
- 75.521839
- Metric
- word error rate (WER)
- Unit
- %
- Benchmark version
- A5Sv2 pinned release commit 64284911a02b38ce07e1d184c56b9c1335f20b57
- Category
- audio
- Direction
- Lower is better
- Sample
- 33679
- Source type
- independent-evaluator
- Evaluator
- AirCaps A5Sv2 ASR benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Exact Mistral API model ID voxtral-mini-transcribe-realtime-2602; native causal streaming with 480 ms transcription delay, real-time paced 560 ms PCM chunks, final transcripts only. One saved run per system and corpus, frozen word-onset v2 references. DiPCo uses five evaluation meetings plus one development meeting, U01.CH1 audio, and fixed +5.1 dB gain.
- Context
- This is a different dataset and protocol from the existing Oct 16 Voxtral results. The benchmark reports one saved run, without repeated trials or a confidence interval. The API model ID is not tied to an immutable serving build. AirCaps says its own A5Sv2 checkpoint was not optimized on the exact Mega-ASR items, but cannot determine whether third-party systems saw overlapping upstream data.
A5Sv2 ASR benchmark, NOTSOFAR eval-small meetings (Show measurement, test conditions, and source)
- Source value
- 45.30037
- Score
- 45.30037
- Metric
- word error rate (WER)
- Unit
- %
- Benchmark version
- A5Sv2 pinned release commit 64284911a02b38ce07e1d184c56b9c1335f20b57
- Category
- audio
- Direction
- Lower is better
- Sample
- 33492
- Source type
- independent-evaluator
- Evaluator
- AirCaps A5Sv2 ASR benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Exact Mistral API model ID voxtral-mini-transcribe-realtime-2602; native causal streaming with 480 ms transcription delay, real-time paced 560 ms PCM chunks, final transcripts only. One saved run per system and corpus, frozen word-onset v2 references. NOTSOFAR uses 22 eval-small meetings and sc_meetup_0/ch0.wav audio.
- Context
- This is a different dataset and protocol from the existing Oct 16 Voxtral results. The benchmark reports one saved run, without repeated trials or a confidence interval. The API model ID is not tied to an immutable serving build. AirCaps says its own A5Sv2 checkpoint was not optimized on the exact Mega-ASR items, but cannot determine whether third-party systems saw overlapping upstream data.
A5Sv2 ASR benchmark, unweighted macro mean across four corpora (Show measurement, test conditions, and source)
- Source value
- 50.52033
- Score
- 50.52033
- Metric
- macro mean of corpus-level word error rates (WER)
- Unit
- %
- Benchmark version
- A5Sv2 pinned release commit 64284911a02b38ce07e1d184c56b9c1335f20b57
- Category
- audio
- Direction
- Lower is better
- Sample
- 4
- Source type
- independent-evaluator
- Evaluator
- AirCaps A5Sv2 ASR benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Arithmetic mean of the four corpus WERs for exact Mistral API model ID voxtral-mini-transcribe-realtime-2602; native causal streaming with 480 ms transcription delay and real-time paced 560 ms PCM chunks. One saved run per system and corpus; fixed corpus selections and frozen word-onset v2 references.
- Context
- This aggregate weights the four corpus WERs equally; it is not the pooled word-level WER. No confidence interval or immutable API serving revision is published.
A5Sv2 ASR benchmark, pooled WER across four corpora (Show measurement, test conditions, and source)
- Source value
- 50.639344
- Score
- 50.639344
- Metric
- pooled word error rate (WER)
- Unit
- %
- Benchmark version
- A5Sv2 pinned release commit 64284911a02b38ce07e1d184c56b9c1335f20b57
- Category
- audio
- Direction
- Lower is better
- Sample
- 133027
- Source type
- independent-evaluator
- Evaluator
- AirCaps A5Sv2 ASR benchmark
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Pooled errors divided by all 133,027 normalized reference words across the four corpora for exact Mistral API model ID voxtral-mini-transcribe-realtime-2602; native causal streaming with 480 ms transcription delay and real-time paced 560 ms PCM chunks. One saved run per system and corpus; frozen word-onset v2 references.
- Context
- This token-pooled aggregate weights corpora by their reference-word counts; it is not the unweighted macro mean. No confidence interval or immutable API serving revision is published.
Page 1 of 9
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
0 to 100, higher is more popular
20 of 83 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 6, 2026
Voxtral Mini Transcribe RealtimeIndex-Echo-S2TT-2B 26Index-Echo-S2TT-9B 24Eleven Flash v2.5 22Lyria Realtime 19
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Voxtral Mini Transcribe Realtime compared
- 1Voxtral Mini Transcribe Realtime vs. Gemini 3.5 Transcribe Live4 shared tests
- 2Voxtral Mini Transcribe Realtime vs. GPT-Live-Transcribe10 shared tests
- 3Voxtral Mini Transcribe Realtime vs. GPT-Realtime-Whisper19 shared tests
- 4Voxtral Mini Transcribe Realtime vs. Scribe v2 Realtime6 shared tests
- 5Voxtral Mini Transcribe Realtime vs. Flux5 shared tests
- 6Voxtral Mini Transcribe Realtime vs. Nova-31 shared test
- 7Voxtral Mini Transcribe Realtime vs. Cartesia Ink-24 shared tests
- 8Voxtral Mini Transcribe Realtime vs. Muse Voice Transcribe6 shared tests
- 9Voxtral Mini Transcribe Realtime vs. Universal-3.6 Pro Realtime1 shared test
Similar models
More models of the same kind as Voxtral Mini Transcribe Realtime, chosen by model line, developer, size, price and release date.
- Voxtral Mini TTSMistral AI · same developer
- Voxtral Mini Transcribe 2Mistral AI · same developer
- Voxtral Mini Transcribe 3Mistral AI · same developer
- Voxtral Mini Transcribe Realtime 3Mistral AI · same developer
- Voxtral Mini TTS 3Mistral AI · same developer
- Voxtral Mini TTS Realtime 3Mistral AI · same developer
- Voxtral Small Transcribe 3Mistral AI · same developer
- pyannote Community-1pyannote · popular in this category
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
API
Further details
Sources and data date
Show all 31 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Vals AI | 1 | 0 | 3 |
Without vendor claims and historical or disputed results; those stay labelled in the single values.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 15, 2026. 25 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | vals-api-serving-revision Note Vals identifies the Voxtral Mini Transcribe Realtime 2602 product and streaming mode but not an immutable API serving revision. |
| Additional source | Mistral model documentation (retrieved September 22, 2026; October 15, 2026) · Mistral AI Voxtral Mini Transcribe Realtime model page · Editorial description reviewed October 2, 2026 |
| Additional source | Vals AI (retrieved November 6, 2026) |
| Additional source | Artificial Analysis (retrieved October 15, 2026) |
| Additional source | Coval (retrieved October 16, 2026; October 17, 2026; October 20, 2026; October 28, 2026; November 2, 2026; November 5, 2026; November 6, 2026) |
| Additional source | Pipecat STT Benchmark (retrieved October 16, 2026) |
| Additional source | AirCaps A5Sv2 ASR benchmark (retrieved October 17, 2026)12 |
| Additional source | Vals AI VoiceCodeBench (retrieved October 17, 2026) |
| Additional source | Pipecat STT Benchmark (retrieved October 19, 2026) |
| Additional source | Model metadata (retrieved October 15, 2026) |
| Additional source | Model metadata (retrieved October 16, 2026)12 |
| Additional source | Model metadata (retrieved October 17, 2026)1234 |
| Additional source | Model metadata (retrieved October 28, 2026)123 |
| Additional source | Model metadata (retrieved November 5, 2026)123 |
| Additional source | Model metadata (retrieved November 6, 2026)123 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |