Skip to main content
Current modelGoogle

Gemini 3.5 Transcribe benchmarks, pricing and specs

Gemini 3.5 Transcribe is a Google model released on August 26, 2026 that takes audio input and produces text. It costs $0.005 per audio minute. It scores 2.6 % WER on Artificial Analysis AA-WER v2, #4 of 6 current models (Artificial Analysis, measured October 13, 2026).

Per audio minute
$0.005
Artificial Analysis AA-WER v2
2.6 % WER · #4/6

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

Share this

Key facts

Provider
Google
Model family
Gemini 3.5
Release date
August 26, 2026
Status
Current
Access
API only
API model id
gemini-3.5-transcribe
Context window
Not reported
Max output
Not reported
Input
audio
Output
text
Task families
audio
Declared capabilities
speech to text, diarization

Gemini 3.5 Transcribe pricing

It is the #5 cheapest of 12 current audio models priced per audio minute.

UnitPrice (USD)TierAppliesSource
1M input tokens$2standardCurrent
1M output tokens$12standardCurrent
1M input tokensNot reportedcachedCurrent
audio minute$0.005estimatedCurrent

Independent benchmark results

Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Google's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.

BenchmarkScoreRankMeasuredSource
Artificial Analysis AA-WER v22.6 % WER#4 of 6October 13, 2026Artificial Analysis · 2026-10-13

Strengths, cautions and best uses

Strengths

  • Detects 85+ languages and handles code-switching within one recording
  • Diarization for up to 8 speakers, word timestamps and up to 1,000 custom vocabulary terms
  • Google estimates the blended cost at about $0.005 per minute of audio

Cautions

  • 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

Best for

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

Alternatives to Gemini 3.5 Transcribe

The closest current audiomodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.

Compare Gemini 3.5 Transcribe with

Other Gemini 3.5 models

Gemini 3.5 Transcribe FAQ

How much does Gemini 3.5 Transcribe cost?

Gemini 3.5 Transcribe costs $0.005 per audio minute at the standard tier. It is the #5 cheapest of 12 current audio models priced per audio minute. Source: Google, verified October 13, 2026.

How does Gemini 3.5 Transcribe score on independent benchmarks?

Gemini 3.5 Transcribe scores 2.6 % WER on Artificial Analysis AA-WER v2, #4 of 6 current models (Artificial Analysis, measured October 13, 2026). These are independent evaluations, not Google's own launch figures.

Is Gemini 3.5 Transcribe open source or API only?

Gemini 3.5 Transcribe is available through Google's API only; its weights are not published.

What are the best alternatives to Gemini 3.5 Transcribe?

The closest current alternatives by price and measured performance are Grok Voice Transcribe 2.0 (67% cheaper per audio minute, $0.001667 vs $0.005), GPT Transcribe (10% cheaper per audio minute, $0.0045 vs $0.005), GPT-4o Transcribe (20% more per audio minute, $0.006 vs $0.005) and Scribe v2 (27% cheaper per audio minute, $0.003667 vs $0.005).

Sources

Cite this page

Van Data Team. "Gemini 3.5 Transcribe Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-13. https://vandatateam.com/ai-model-benchmarks/gemini-3-5-transcribe

Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.

Production evaluation

Deciding whether Gemini 3.5 Transcribe fits your workload?

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

  • Evaluation cases and acceptance thresholds tied to real work
  • Model routing, fallbacks and cost controls