Skip to main content

audio model comparison

Gemini 3.5 Transcribe vs Scribe v2

Gemini 3.5 Transcribe and Scribe v2 are both current audio models, from Google and ElevenLabs. Scribe v2 is 27% cheaper per audio minute than Gemini 3.5 Transcribe, $0.003667 vs $0.005. On Artificial Analysis AA-WER v2, Gemini 3.5 Transcribe scores 2.6 % WER and Scribe v2 2.18 % WER (Artificial Analysis, measured October 13, 2026).

Data verified October 13, 2026 · Dataset 2026-10-13

Share this

Side by side

Standard-tier prices in effect today. The better value in each row is highlighted.

FactGemini 3.5 TranscribeScribe v2
Price per audio minute$0.005$0.003667 (better)
Artificial Analysis AA-WER v22.6 % WER (#4 of 6)2.18 % WER (#2 of 6) (better)
ProviderGoogleElevenLabs
Release dateAugust 26, 2026January 9, 2026
AccessAPI onlyAPI only
Context windowNot reportedNot reported
Max outputNot reportedNot reported
Inputaudioaudio
Outputtexttext

Scores:Artificial Analysis · 2026-10-13

Open both in the interactive comparison

When to choose each

Gemini 3.5 Transcribe

Best for

  • Batch transcription with speaker labels
  • Multilingual meeting and call transcripts

Watch out for

  • One hour of audio per request, or 30 minutes with diarization or timestamps
  • Custom vocabulary cannot be combined with diarization or timestamps, and there is no Batch API
Full Gemini 3.5 Transcribe profile

Scribe v2

Best for

  • Batch transcription and diarization

Watch out for

  • $0.22 per hour of audio; keyterm prompting and transcript editing add $0.05 and $0.07 per hour
Full Scribe v2 profile

Gemini 3.5 Transcribe vs Scribe v2 FAQ

Which is cheaper, Gemini 3.5 Transcribe or Scribe v2?

Scribe v2 is 27% cheaper per audio minute than Gemini 3.5 Transcribe, $0.003667 vs $0.005.

Which scores higher on independent benchmarks, Gemini 3.5 Transcribe or Scribe v2?

Scribe v2 leads on Artificial Analysis AA-WER v2, 2.18 % WER to 2.6 % WER. Scores are independent evaluations, not either vendor's launch figures.

Production evaluation

Choosing between Gemini 3.5 Transcribe and Scribe v2?

Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • A head-to-head evaluation on your real workload
  • Routing between models by cost and difficulty