DEEPGRAMTEXT-TO-SPEECH11,890 SAMPLES / 30 DAYSLAST RUN NOV 21, 2026, 02:00 UTC
Aura 2 En text-to-speech benchmarks
Aura 2 En, hosted by Cloudflare, measures mean 515 ms time to first audio (29th of 32) and 1.9% word error rate (25th of 32) among TTS systems. Results cover the last 30 days. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .
Coval has active text-to-speech measurements for Aura 2 En, created by Deepgram and served on Cloudflare.
- Time to First Audio#29 / 32
- 515ms
- TTFA Network Roundtrip#29 / 32
- 321ms
- TTFA Leading Silence#31 / 32
- 194ms
- Word Error Rate#25 / 32
- 1.9%
Overview
Aura 2 En is tested every day on a fixed set of text prompts, measuring how quickly audible speech starts and how intelligible the result is.
Technical specifications
- Made by
- Deepgram
- Hosted by
- Cloudflare
- Source
- Shared inference
- Licensing
- Proprietary
- Deployment
- Cloud
- Region
- US
How Aura 2 En ranks
Full TTS dashboard- #7Qwen3 TTS 1.7bDedicated inference. Shared endpoints serve many customers on the same infrastructure, while dedicated endpoints run on hardware reserved for a single customer.105 ms
Show all 32 modelsShow fewer
- #17Qwen3 TTS 1.7bDedicated inference. Shared endpoints serve many customers on the same infrastructure, while dedicated endpoints run on hardware reserved for a single customer.1.7%
Show all 32 modelsShow fewer
Highest relative placement: 25th of 32 on Word Error Rate.
Latency vs accuracy
Where the errors come from
- Aura 2 En1.9%
Averages and tail latency
Averages hide slow outliers — these are the distributions behind each figure.
- Time to First Audiop50 515 ms · Max 5670 ms
- TTFA Network Roundtripp50 266 ms · Max 5670 ms
- TTFA Leading Silencep50 183 ms · Max 1255 ms
- Aura 2 Enp50 0.0% · Max 55.6%
| Metric | Average | p25 | p50 | p75 | p90 | p95 | Max | Samples |
|---|---|---|---|---|---|---|---|---|
| Time to First Audio | 515 ms | 339 ms | 515 ms | 621 ms | 735 ms | 871 ms | 5670 ms | 2,866 |
| TTFA Network Roundtrip | 321 ms | 226 ms | 266 ms | 346 ms | 481 ms | 617 ms | 5670 ms | 2,866 |
| TTFA Leading Silence | 194 ms | 67 ms | 183 ms | 331 ms | 368 ms | 388 ms | 1255 ms | 2,866 |
| Word Error Rate | 1.9% | 0.0% | 0.0% | 3.2% | 9.1% | 15.2% | 55.6% | 2,814 |
Last 30 days
Daily medians from the same measurement runs · gaps are days without qualifying runs.
How fast is Aura 2 En?
On Cloudflare, Aura 2 En measures mean 515 ms time to first audio (29th of 32). Last measured 2026-11-21.
How accurate is Aura 2 En?
On Cloudflare, Aura 2 En measures 1.9% word error rate (25th of 32). Last measured 2026-11-21.
Who hosts Aura 2 En?
Aura 2 En is created by Deepgram and served by Cloudflare. Coval measures each hosted endpoint separately.
Results are re-measured daily using fixed datasets and reported over a rolling 30-day window. Same datasets, prompts and metric definitions for every model, measured by Coval’s open-source runner. Full methodology on the overview.
Evaluate your own voice agent
Use Coval to test your production configuration, prompts and calls—not only the public benchmark endpoints.