TTFAactiveAudio
TTFA: Time to First Audio (ms)
Metric: ms (lower is better)Introduced: 2024
Time in milliseconds from the end of a user utterance until the first audio byte is received from the model, measured at representative API endpoints by Artificial Analysis (P50). Sub-300 ms is generally imperceptible; 200 ms matches natural human turn-taking. Lower is better.
Models ranked
4
tracked on this benchmark
Score band
630.0 – 1140.0
best → lowest tracked
Snapshot trend
—
need ≥2 snapshots
Leaderboard
Tracked models ranked by ms (lower is better).
#Model variant and provenanceRelative to leaderScore
1
Gemini 2.5 Flash Live API
630.0Version: p50-msHarness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
2
Grok Voice Think Fast 1.0
780.0Version: p50-msHarness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
3
gpt-realtime-1.5
820.0Version: p50-msHarness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
4
Amazon Nova 2 Sonic
1140.0Version: p50-msHarness: Not recordedEvaluator: Not recordedObserved: Jun 7, 2026Confidence: Not recordedSource
How to read this benchmark
This benchmark scores models where lower is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Jun 7, 2026