GoogleDeepgramAudio matchupSpeech to text
Gemini 3.5 Transcribevs.Nova-3
Which model is better?
Gemini 3.5 Transcribe is slightly ahead in independent tests, but the lead is not certain.
Independent testsArtificial Analysis
Gemini 3.5 Transcribe0 of 1
Nova-30 of 1
Popularityout of 100
Gemini 3.5 Transcribe52
Nova-351
Weights and access
Gemini 3.5 Transcribeproprietary
Nova-3proprietary
Priceverbatim from the provider
Gemini 3.5 Transcribe$2 per 1M audio tokens ($0.003 per audio minute)
Nova-3n/a
Pick Gemini 3.5 Transcribe for
leaning Artificial Analysis
Pick Nova-3 for
No clear edge
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
Artificial Analysis
Gemini 3.5 Transcribe slightly aheadArtificial Analysis AA-WER (non-streaming)
Gemini 3.5 Transcribe2.6 %
Nova-35.2 %
lower is better, as of October 15, 2026
Source · latest October 15, 2026
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| Gemini 3.5 Transcribe | Nova-3 | |
|---|---|---|
| Task | Speech to text | Speech to text |
| Developer | Deepgram | |
| Status | Active | Active |
| Weights | proprietary | proprietary |
| Runs locally | no | no |
| Price | $2 per 1M audio tokens ($0.003 per audio minute) | n/a |
| Popularity (out of 100) | 52 | 51 |