OpenAIGoogleAudio matchupSpeech to text
GPT-Realtime-Whispervs.Gemini 3.5 Transcribe Live
Which model is better?
Gemini 3.5 Transcribe Live is slightly ahead in independent tests, but the lead is not certain.
Pick GPT-Realtime-Whisper for
Pick Gemini 3.5 Transcribe Live for
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”.
Coval
Gemini 3.5 Transcribe Live slightly aheadGemini 3.5 Transcribe Live is clearly ahead in 0 of 16 subtests and slightly in 9, GPT-Realtime-Whisper in 0 clearly and slightly in 1. 6 are level.
Coval Time to Final Segment (TTFS) maximum
lower is better, as of November 5, 2026
Coval RTF maximum
lower is better, as of November 5, 2026
Coval Time to Final Segment (TTFS) p50
lower is better, as of November 5, 2026
Show all 16 subtests
| Subtest | GPT-Realtime-Whisper | Gemini 3.5 Transcribe Live | Verdict |
|---|---|---|---|
| Coval Time to Final Segment (TTFS) maximum (lower is better) | 20,386 ms | 5,018 ms | Gemini 3.5 Transcribe Live slightly ahead |
| Coval RTF maximum (lower is better) | 5.55 | 3.12 | Gemini 3.5 Transcribe Live slightly ahead |
| Coval Time to Final Segment (TTFS) p50 (lower is better) | 547 ms | 325 ms | Gemini 3.5 Transcribe Live slightly ahead |
| Coval AudioToFinal maximum (lower is better) | 30.01 s | 18.79 s | Gemini 3.5 Transcribe Live slightly ahead |
| Coval Time to Final Segment (TTFS) mean (lower is better) | 564 ms | 381 ms | Gemini 3.5 Transcribe Live slightly ahead |
| Coval pooled corpus Word Error Rate (WER) (lower is better) | 4.0 % | 2.9 % | Gemini 3.5 Transcribe Live slightly ahead |
| Coval Word Error Rate (WER) per-sample mean (lower is better) | 4.5 % | 3.4 % | Gemini 3.5 Transcribe Live slightly ahead |
| Coval Time to First Token (TTFT) p50 (lower is better) | 1,878 ms | 1,475 ms | Gemini 3.5 Transcribe Live slightly ahead |
| Coval Time to First Token (TTFT) mean (lower is better) | 1,820 ms | 1,533 ms | Gemini 3.5 Transcribe Live slightly ahead |
| Coval Time to First Token (TTFT) maximum (lower is better) | 10,968 ms | 12,993 ms | GPT-Realtime-Whisper slightly ahead |
| Coval RTF mean (lower is better) | 1.09 | 1.06 | level |
| Coval RTF p50 (lower is better) | 1.07 | 1.04 | level |
| Coval AudioToFinal p50 (lower is better) | 8.88 s | 8.67 s | level |
| Coval AudioToFinal mean (lower is better) | 8.51 s | 8.32 s | level |
| Coval Word Error Rate (WER) per-sample maximum (lower is better) | 100.0 % | 100.0 % | level |
| Coval Word Error Rate (WER) per-sample p50 (lower is better) | 0.0 % | 0.0 % | level |
Source · latest November 5, 2026
Pipecat STT Benchmark
Gemini 3.5 Transcribe Live slightly aheadGemini 3.5 Transcribe Live is clearly ahead in 0 of 2 subtests and slightly in 2, GPT-Realtime-Whisper in none.
Pipecat STT Benchmark semantic WER mean
lower is better, as of October 16, 2026
Pipecat STT Benchmark semantic pooled WER
lower is better, as of October 16, 2026
Source · latest October 16, 2026
Artificial Analysis
Gemini 3.5 Transcribe Live slightly aheadArtificial Analysis AA-WER Streaming (final transcription)
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.
| GPT-Realtime-Whisper | Gemini 3.5 Transcribe Live | |
|---|---|---|
| Task | Speech to text | Speech to text |
| Developer | OpenAI | |
| Status | Active | Active |
| Weights | proprietary | proprietary |
| Runs locally | no | no |
| Price | $0.017 per audio minute | $3.50 per 1M audio tokens ($0.005 per audio minute) |
| Popularity (out of 100) | 34 | 35 |