OpenAIAudio modelDeprecated

GPT-4o Mini Transcribe

PopularityRank 408 of 631

33out of 100same as last month

based on two data groups, mostly search

Summary

GPT-4o Mini Transcribe is a compact speech-to-text model built on GPT-4o Mini. OpenAI documents improvements in word error rate, language recognition, and accuracy compared with the original Whisper models. It accepts audio and returns text. With a 16,000-token context and a 2,000-token maximum output, its role stays focused on transcription.

However, OpenAI has announced its removal from the API on February 26, 2027, and names GPT-Transcribe and GPT-Live-Transcribe as replacements.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 98 published benchmark results

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.

Artificial Analysis AA-WER (non-streaming) (Show measurement, test conditions, and source)

Source value: 4.5
Score: 4.5
Metric: word error rate (WER)
Unit: %
Benchmark version: AA-WER v2.2
Category: audio
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-10-15
Methodology: Independent evaluation. Artificial Analysis directly tested the named API endpoint; audio-duration-weighted WER across AA-AgentTalk (50%), VoxPopuli-Cleaned-AA English (25%), and Earnings22-Cleaned-AA (25%), about eight hours total. Current normalizer AA-WER v2.2.

Source Artificial Analysis

Coval rolling-30-day pooled word error rate (gpt-4o-mini-transcribe endpoint) (Show measurement, test conditions, and source)

Source value: 3.883108102175039
Score: 3.883108102175039
Metric: Pooled word error rate across Coval's fixed public speech-recognition audio conditions
Unit: %
Benchmark version: Coval rolling 30-day snapshot, last measured 2026-10-16, source response fetched 2026-10-16T15:36:04.022422Z
Category: audio
Direction: Lower is better
Sample: 26641
Source type: independent-evaluator
Evaluator: Coval
Status: active
Retrieved at: 2026-10-16
Methodology: Independent evaluation. Exact hosted API model ID gpt-4o-mini-transcribe. Coval reports its daily fixed-public-audio endpoint benchmark over a rolling 30-day window, last measured 2026-10-16. Stored score is pooled_value=3.883108102175039 from the WER row, not mean_value; Coval's visible 3.9% is rounded to one decimal. The reported WER sample count comes from the same row.
Context: Coval's WER row gives scored sample count only. Total attempted requests and failures are not published, and no confidence interval is reported. This Coval setup is separate from Artificial Analysis AA-WER; the results should not be merged or presented as the same benchmark.

Source Coval (unavailable on November 2, 2026) https://benchmarks.coval.ai/models/gpt-4o-mini-transcribe

GPT-4o mini Transcribe, Voxtral Realtime paper Table 3 English short-form macro-average WER (Show measurement, test conditions, and source)

Source value: 7.93
Score: 7.93
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Table 3
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English short-form macro-average WER. The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 3 macro-averages English results across tasks.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Table 3 English long-form macro-average WER (Show measurement, test conditions, and source)

Source value: 7.97
Score: 7.97
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Table 3
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English long-form macro-average WER. The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 3 macro-averages English results across tasks.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Table 3 FLEURS macro-average error rate (Show measurement, test conditions, and source)

Source value: 7.95
Score: 7.95
Metric: macro-average error rate (WER except CER for Japanese and Chinese)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Table 3
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); FLEURS macro-average error rate. The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 3 averages across languages; Japanese and Chinese use CER, while other languages use WER.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Table 3 Mozilla Common Voice macro-average error rate (Show measurement, test conditions, and source)

Source value: 12.85
Score: 12.85
Metric: macro-average error rate (WER except CER for Japanese and Chinese; Arabic excluded from this macro-average)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Table 3
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); Mozilla Common Voice macro-average error rate. The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 3 averages across languages and excludes Arabic from the MCV macro-average; Japanese and Chinese use CER, while other languages use WER.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Appendix Table 5 English short-form WER: LibriSpeech Test Clean (LS-C) (Show measurement, test conditions, and source)

Source value: 1.94
Score: 1.94
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Appendix Table 5
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English short-form WER: LibriSpeech Test Clean (LS-C). The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 5 reports dataset-level WER; its AVG cell is omitted here because the same macro-average appears in Table 3.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Appendix Table 5 English short-form WER: LibriSpeech Test Other (LS-O) (Show measurement, test conditions, and source)

Source value: 4.48
Score: 4.48
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Appendix Table 5
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English short-form WER: LibriSpeech Test Other (LS-O). The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 5 reports dataset-level WER; its AVG cell is omitted here because the same macro-average appears in Table 3.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Appendix Table 5 English short-form WER: GigaSpeech (GS) (Show measurement, test conditions, and source)

Source value: 10.67
Score: 10.67
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Appendix Table 5
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English short-form WER: GigaSpeech (GS). The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 5 reports dataset-level WER; its AVG cell is omitted here because the same macro-average appears in Table 3.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Appendix Table 5 English short-form WER: VoxPopuli (VP) (Show measurement, test conditions, and source)

Source value: 6.79
Score: 6.79
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Appendix Table 5
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English short-form WER: VoxPopuli (VP). The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 5 reports dataset-level WER; its AVG cell is omitted here because the same macro-average appears in Table 3.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Appendix Table 5 English short-form WER: SwitchBoard (SB) (Show measurement, test conditions, and source)

Source value: 11.15
Score: 11.15
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Appendix Table 5
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English short-form WER: SwitchBoard (SB). The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 5 reports dataset-level WER; its AVG cell is omitted here because the same macro-average appears in Table 3.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

GPT-4o mini Transcribe, Voxtral Realtime paper Appendix Table 5 English short-form WER: CallHome (CH) (Show measurement, test conditions, and source)

Source value: 15.54
Score: 15.54
Metric: word error rate (WER)
Unit: %
Benchmark version: Voxtral Realtime arXiv:2602.11298v3, Appendix Table 5
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: Mistral AI, Voxtral Realtime paper
Status: active
Retrieved at: 2026-10-16
Methodology: Vendor-reported result. Exact paper result row "GPT-4o mini Transcribe" mapped by name to local profile "gpt-4o-mini-transcribe" (GPT-4o Mini Transcribe); English short-form WER: CallHome (CH). The paper does not specify an immutable served API snapshot or per-metric evaluated sample count. Table 5 reports dataset-level WER; its AVG cell is omitted here because the same macro-average appears in Table 3.
Context: Mistral-authored comparison; the paper identifies the row as GPT-4o mini Transcribe, but does not state an immutable served API snapshot. The paper does not publish a metric-specific evaluated sample count or confidence interval.

Source Mistral AI, Voxtral Realtime paper

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 45 models

pyannote Community-173

Nemotron-3-Diarization57

Gemini 3.5 Transcribe52

Confucius4-R2T252

NVIDIA Nemotron 3.5 Transcribe52

Granite Speech 5.0 470M TurboCTC52

Kokoro-82M51

Nova-351

Fish Audio S2 Pro51

Granite Speech 5.0 470M TurboCTC NC50

Orukeet49

Lyria 3.547

Gemini 3.5 Live Translate46

Phonon-244

Aura-244

Gemini 3.1 Flash TTS44

MiniMax-Music341

Audio8-ASR-Infinite41

GPT-Realtime 2.141

GPT-4o Mini Transcribe33

pyannote Community-1

Nemotron-3-Diarization

Gemini 3.5 Transcribe

Confucius4-R2T2

NVIDIA Nemotron 3.5 Trans…

Granite Speech 5.0 470M T…

Kokoro-82M

Nova-3

Fish Audio S2 Pro

Granite Speech 5.0 470M T…

Orukeet

Lyria 3.5

Gemini 3.5 Live Translate

GPT-4o Mini Transcribe

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 7, 2026

GPT-4o Mini TranscribeGemini 3.5 Transcribe Live 35GPT-Realtime Translate 35GPT-Realtime-Whisper 34GPT-Transcribe 32

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.

GPT-4o Mini Transcribe compared

Similar models

More models of the same kind as GPT-4o Mini Transcribe, chosen by model line, developer, size, price and release date.

All specifications

Architecture

Model class: Speech recognition; Source: Model class
Knowledge cutoff: Jun 1, 2024; Source: Knowledge cutoff

Input and output

Input: Audio; Source: Input
Output: Text; Source: Output
Context window: 16,000 tokens; Source: Context window
Maximum output: 2,000 tokens; Source: Maximum output
Capabilities: Improved word error rate and language recognition compared with the original Whisper models; Source: Capabilities

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

Access: API; Source: Access

API

API model ID: gpt-4o-mini-transcribe; Source: API model ID

Further details

Task: Transcription; Source: Task
Supported details: Compact GPT-4o transcription model; Source: Supported details
Shutdown: Scheduled for February 26, 2027; OpenAI recommends GPT-Transcribe or GPT-Live-Transcribe; Source: Shutdown

Prices

Shutdown announced for February 26, 2027.

Audio input price: $1.25 per 1M audio tokensSource
Documented output price: $5 per 1M tokens (listed under audio tokens; audio output is not supported)Source

Sources and data date

Show all 24 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
Artificial Analysis	0	0	1

Without vendor claims and historical or disputed results; those stay labelled in the single values. 1 measurements are not yet assigned to a test series.

Type	Evidence and data date
Research status	Research date October 15, 2026. 19 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Unresolved	medical-benchmark Note SLPHelm reports Disorder Diagnosis Micro F1 0.466 ± 0.018 for the exact GPT-4o Mini Transcribe label in a specialized pediatric speech-language-pathology evaluation. The ± value is mean ± bootstrap standard deviation, not a 95% confidence interval. The checked MedDictate table still has no result. This is not a general ASR benchmark; metric-specific N, immutable served API snapshot and evaluation date remain unknown. These results do not establish clinical validity.
Not published	immutable-evaluated-api-snapshot Note The paper names GPT-4o mini Transcribe but does not disclose the immutable API/model snapshot evaluated; the exact product name is the available profile bridge.
Not published	evaluated-denominator-and-confidence-interval Note The paper tables do not publish the metric-specific evaluated sample count or confidence intervals; no denominator was inferred from corpus sizes.
Unresolved	slphelm-model-n-and-api-revision Note The paper does not report a metric-specific evaluated N or immutable served API snapshot for the exact-name row; the reported ± values are bootstrap standard deviations, not CIs.
Not found in the inspected sources	Current Coval endpoint benchmark values Note The exact model endpoint is no longer available on its public model page, and the live task leaderboards do not contain an exact row. Historic research is retained; this refresh has no numeric score.
Additional source	OpenAI model documentation (retrieved September 24, 2026; October 15, 2026; October 16, 2026; October 17, 2026) · OpenAI GPT-4o Mini Transcribe model documentation · Editorial description reviewed October 2, 2026
Additional source	Model lifecycle (retrieved September 24, 2026) · OpenAI model deprecations · Editorial description reviewed October 2, 2026
Additional source	Artificial Analysis (retrieved October 15, 2026)
Additional source	Coval (retrieved October 16, 2026; October 17, 2026) (unavailable on November 2, 2026) https://benchmarks.coval.ai/models/gpt-4o-mini-transcribe
Additional source	Mistral AI, Voxtral Realtime paper (retrieved October 16, 2026)
Additional source	Omi Health PriMock57 benchmark (retrieved October 17, 2026)1 2
Additional source	Speko speech-to-text benchmarks (retrieved October 17, 2026)
Additional source	SLPHelm paper authors (EMNLP 2025) (retrieved October 19, 2026)
Additional source	Perit PERIT-STT leaderboard (retrieved October 19, 2026)
Additional source	Ocular Converse-STT Benchmark (retrieved October 21, 2026)
Additional source	Perit PERIT-STT leaderboard (retrieved October 22, 2026)
Additional source	Model metadata (retrieved October 15, 2026)
Additional source	Model metadata (retrieved October 17, 2026)1 2
Additional source	Model metadata (retrieved October 28, 2026)1 2 3
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