ElevenLabsAudio modelActive

Scribe v2 Medical

Popularityhardly any signal

under 1out of 100same as last month

Summary

Scribe v2 Medical is a batch transcription model fine-tuned for clinical audio. ElevenLabs reports 35% fewer transcription errors on clinical audio than Scribe v2, especially around medication names, anatomy, pathology, and clinical dictation. The provider says everyday speech retains the general model’s accuracy.

The result remains a draft for documentation. A healthcare professional or another authorized reviewer must check and correct it before use. The model does not diagnose conditions or provide treatment recommendations. For live transcription, ElevenLabs points to Scribe v2 Realtime, not this clinical batch variant.

All benchmark results

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

Show all 23 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.

ElevenLabs MedDictate overall WER (Show measurement, test conditions, and source)

Source value: 4.9
Score: 4.9
Metric: overall WER
Unit: %
Benchmark version: Corti MedDictate; evaluator edition not stated
Category: audio
Direction: Lower is better
Sample: 40
Source type: vendor-reported
Evaluator: ElevenLabs model evaluation
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Vendor evaluation on Corti MedDictate: English, French, and German clinical dictation. The public test split has 40 clips (24 EN, 7 FR, 9 DE); overall aggregation details are not stated.

Source ElevenLabs model evaluation

ElevenLabs MedTerm medical-term recall (Show measurement, test conditions, and source)

Source value: 77.7
Score: 77.7
Metric: recall of annotated medical terms
Unit: %
Benchmark version: Corti MedTerm (600 samples)
Category: audio
Direction: Higher is better
Sample: 600
Source type: vendor-reported
Evaluator: ElevenLabs model evaluation
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Vendor evaluation on Corti MedTerm, a public 600-sample clinical-terminology benchmark; term-WER scores annotated medical terms only.

Source ElevenLabs model evaluation

ElevenLabs MedTerm medical-term WER (Show measurement, test conditions, and source)

Source value: 10.4
Score: 10.4
Metric: term-WER
Unit: %
Benchmark version: Corti MedTerm (600 samples)
Category: audio
Direction: Lower is better
Sample: 600
Source type: vendor-reported
Evaluator: ElevenLabs model evaluation
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Vendor evaluation on Corti MedTerm, a public 600-sample clinical-terminology benchmark; term-WER scores annotated medical terms only.

Source ElevenLabs model evaluation

ElevenLabs Eka Medical ASR semantic WER (Show measurement, test conditions, and source)

Source value: 6.5
Score: 6.5
Metric: semantic WER
Unit: %
Benchmark version: Eka Medical ASR; evaluator edition not stated
Category: audio
Direction: Lower is better
Sample: 3619
Source type: vendor-reported
Evaluator: ElevenLabs model evaluation
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Vendor evaluation on public Eka Medical ASR, 3,619 English clinical-audio samples; semantic WER counts meaning-equivalent formatting as equivalent.

Source ElevenLabs model evaluation

ElevenLabs Eka Medical ASR keyword WER (Show measurement, test conditions, and source)

Source value: 6.02
Score: 6.02
Metric: keyword WER
Unit: %
Benchmark version: Eka Medical ASR; evaluator edition not stated
Category: audio
Direction: Lower is better
Sample: 3619
Source type: vendor-reported
Evaluator: ElevenLabs model evaluation
Status: active
Retrieved at: 2026-10-15
Methodology: Vendor-reported result. Vendor evaluation on public Eka Medical ASR, 3,619 English clinical-audio samples; keyword-WER scores annotated medical keywords only.

Source ElevenLabs model evaluation

Eka Medical ASR WER on isolated single-word terms (Show measurement, test conditions, and source)

Source value: 14.3
Score: 14.3
Metric: word error rate on isolated annotated terms
Unit: %
Benchmark version: Eka Medical ASR; isolated-term subset
Category: speech-to-text
Direction: Lower is better
Source type: vendor-reported
Evaluator: ElevenLabs Scribe v2 Medical evaluation
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. ElevenLabs-reported Eka Medical ASR result on the public dataset described as 3,619 English clinical audio samples with medical-term annotations. The row is a term-level WER subset, not the existing whole-transcript semWER or the existing whole-set keyword-WER row. The source describes clinical sentence and isolated single-term conditions but does not give their per-subset sample counts or scoring procedure.
Context: Subset N and confidence intervals are not published. The aggregate annotated-term figure of 9.5% was excluded because its relationship to the existing Eka keyword-WER row is not clear enough to avoid a duplicate.

Source ElevenLabs Scribe v2 Medical evaluation

Eka Medical ASR term WER in clinical sentences (Show measurement, test conditions, and source)

Source value: 7.5
Score: 7.5
Metric: medical-term word error rate
Unit: %
Benchmark version: Eka Medical ASR; clinical-sentence subset
Category: speech-to-text
Direction: Lower is better
Source type: vendor-reported
Evaluator: ElevenLabs Scribe v2 Medical evaluation
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. ElevenLabs-reported Eka Medical ASR result on the public dataset described as 3,619 English clinical audio samples with medical-term annotations. The row is a term-level WER subset, not the existing whole-transcript semWER or the existing whole-set keyword-WER row. The source describes clinical sentence and isolated single-term conditions but does not give their per-subset sample counts or scoring procedure.
Context: Subset N and confidence intervals are not published. The aggregate annotated-term figure of 9.5% was excluded because its relationship to the existing Eka keyword-WER row is not clear enough to avoid a duplicate.

Source ElevenLabs Scribe v2 Medical evaluation

Corti MedDictate clinical dictation WER, English (Show measurement, test conditions, and source)

Source value: 3
Score: 3
Metric: Word error rate (WER)
Unit: %
Benchmark version: Corti MedDictate; ElevenLabs evaluation article updated 2026-10-12
Category: speech recognition
Direction: Lower is better
Source type: vendor-reported
Evaluator: ElevenLabs, Scribe v2 Medical evaluation
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Official ElevenLabs comparison on Corti MedDictate clinical dictation; exact source table label "Scribe v2 Medical" and model_id=scribe_v2_medical; locale EN; reported metric WER. Locale sample count, decoding settings, and immutable serving revision are not published.
Context: Vendor-reported result; the article does not publish locale-level N, decoding settings, or an immutable served-model revision. This locale row is distinct from the article's already-recorded overall WER.

Source ElevenLabs, Scribe v2 Medical evaluation

Corti MedDictate clinical dictation WER, French (Show measurement, test conditions, and source)

Source value: 8.3
Score: 8.3
Metric: Word error rate (WER)
Unit: %
Benchmark version: Corti MedDictate; ElevenLabs evaluation article updated 2026-10-12
Category: speech recognition
Direction: Lower is better
Source type: vendor-reported
Evaluator: ElevenLabs, Scribe v2 Medical evaluation
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Official ElevenLabs comparison on Corti MedDictate clinical dictation; exact source table label "Scribe v2 Medical" and model_id=scribe_v2_medical; locale FR; reported metric WER. Locale sample count, decoding settings, and immutable serving revision are not published.
Context: Vendor-reported result; the article does not publish locale-level N, decoding settings, or an immutable served-model revision. This locale row is distinct from the article's already-recorded overall WER.

Source ElevenLabs, Scribe v2 Medical evaluation

Corti MedDictate clinical dictation WER, German (Show measurement, test conditions, and source)

Source value: 7.2
Score: 7.2
Metric: Word error rate (WER)
Unit: %
Benchmark version: Corti MedDictate; ElevenLabs evaluation article updated 2026-10-12
Category: speech recognition
Direction: Lower is better
Source type: vendor-reported
Evaluator: ElevenLabs, Scribe v2 Medical evaluation
Status: active
Retrieved at: 2026-10-17
Methodology: Vendor-reported result. Official ElevenLabs comparison on Corti MedDictate clinical dictation; exact source table label "Scribe v2 Medical" and model_id=scribe_v2_medical; locale DE; reported metric WER. Locale sample count, decoding settings, and immutable serving revision are not published.
Context: Vendor-reported result; the article does not publish locale-level N, decoding settings, or an immutable served-model revision. This locale row is distinct from the article's already-recorded overall WER.

Source ElevenLabs, Scribe v2 Medical evaluation

Scribe v2 Medical, M-WER (Show measurement, test conditions, and source)

Source value: 1.08
Score: 1.08
Metric: Medical word error rate over medical reference tokens
Unit: %
Benchmark version: Omi Health Medical Speech-to-Text Benchmark, edition 2026-09-26.1; batch
Category: speech-to-text
Direction: Lower is better
Sample: 1513
Source type: community-reported
Evaluator: Omi Health Medical Speech-to-Text Benchmark
Status: active
Retrieved at: 2026-10-17
Methodology: Community-reported result. Omi Health Medical Speech-to-Text Benchmark, edition 2026-09-26.1, batch transcription. Exact table row “ElevenLabs Scribe v2 Medical”; 1,513 English recordings totaling 7.2 hours. The table states 2,872 medical reference tokens, 442 drug references, and 94 dose/unit events. Batch latency uses 600 measurements; Omi says ElevenLabs endpoints were timed from Frankfurt in September 2026.
Context: Omi Health sells a competing commercial medical speech-to-text product. Treat this benchmark conservatively as a community/vendor report, not a neutral independent replication. Omi does not state an immutable model revision, complete decoder parameters, or confidence intervals. Results apply only to the stated Omi test edition and route.

Source Omi Health Medical Speech-to-Text Benchmark

Scribe v2 Medical, drug-term error rate (Show measurement, test conditions, and source)

Source value: 0.45
Score: 0.45
Metric: Errors over drug-term references
Unit: %
Benchmark version: Omi Health Medical Speech-to-Text Benchmark, edition 2026-09-26.1; batch
Category: speech-to-text
Direction: Lower is better
Sample: 1513
Source type: community-reported
Evaluator: Omi Health Medical Speech-to-Text Benchmark
Status: active
Retrieved at: 2026-10-17
Methodology: Community-reported result. Omi Health Medical Speech-to-Text Benchmark, edition 2026-09-26.1, batch transcription. Exact table row “ElevenLabs Scribe v2 Medical”; 1,513 English recordings totaling 7.2 hours. The table states 2,872 medical reference tokens, 442 drug references, and 94 dose/unit events. Batch latency uses 600 measurements; Omi says ElevenLabs endpoints were timed from Frankfurt in September 2026.
Context: Omi Health sells a competing commercial medical speech-to-text product. Treat this benchmark conservatively as a community/vendor report, not a neutral independent replication. Omi does not state an immutable model revision, complete decoder parameters, or confidence intervals. Results apply only to the stated Omi test edition and route.

Source Omi Health Medical Speech-to-Text Benchmark

Page 1 of 2

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

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

Scribe v2 Medical0

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

Scribe v2 Medical

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

Over time

Weekly values from October 18, 2026 to November 6, 2026

Scribe v2 MedicalAmazon Nova 2 Sonic 0Eleven Multilingual STS v2 0Eleven Music v2.5 0Eleven Text to Sound v2 0

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.

Similar models

More models of the same kind as Scribe v2 Medical, chosen by model line, developer, size, price and release date.

All specifications

Architecture

Model class: Medical speech recognition; Source: Model class

Input and output

Input: Audio; Source: Input
Output: Text; Source: 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

Access: API; Source: Access

API

API model ID: scribe_v2_medical; Source: API model ID

Further details

Task: Medical transcription; Source: Task
Supported details: Focused on medical transcription; Source: Supported details
Medical speech: Over 90 languages; ElevenLabs reports 35% fewer transcription errors on clinical audio than Scribe v2; Source: Medical speech
Intended use: For clinical transcription, not for diagnosis or treatment recommendations; Source: Intended use

Sources and data date

Show all 15 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

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. 9 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	independent-benchmark Note No independent-evaluator result for exact Scribe v2 Medical was found; the clinical rows in this bundle are published by ElevenLabs and remain vendor-reported.
Not found in the inspected sources	independent-benchmark Note No independent-evaluator result for exact Scribe v2 Medical was found; its clinical ASR rows remain vendor-reported.
Not published	Eka Medical ASR subset N Note The article reports 3,619 samples for the full dataset but no scored counts for the clinical-sentence or isolated-term subsets.
Additional source	ElevenLabs model documentation (retrieved September 24, 2026; October 15, 2026) · ElevenLabs Models documentation · Editorial description reviewed October 2, 2026
Additional source	ElevenLabs model evaluation (retrieved October 15, 2026; October 17, 2026; October 18, 2026)
Additional source	Omi Health Medical Speech-to-Text Benchmark (retrieved October 17, 2026; October 18, 2026)
Additional source	Deepgram Nova-3 Medical Multilingual article (retrieved October 18, 2026)
Additional source	Model metadata (retrieved October 15, 2026)1 2 3 4
Additional source	Model metadata (retrieved October 17, 2026)
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