DEEPGRAMTEXT-TO-SPEECH9,912 SAMPLES / 30 DAYSLAST RUN NOV 21, 2026, 03:30 UTC
Flux TTS text-to-speech benchmarks
Flux TTS, hosted by Deepgram, measures mean 218 ms time to first audio (14th of 32) and 1.8% word error rate (21st 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 Flux TTS, created by Deepgram and served through Deepgram's own API.
- Time to First Audio#14 / 32
- 218ms
- TTFA Network Roundtrip#17 / 32
- 166ms
- TTFA Leading Silence#17 / 32
- 53ms
- Word Error Rate#21 / 32
- 1.8%
Overview
Flux TTS is tested every day on a fixed set of text prompts, measuring how quickly audible speech starts and how intelligible the result is.
How Flux TTS 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%
Latency vs accuracy
Where the errors come from
- Flux TTS1.8%
Averages and tail latency
Averages hide slow outliers — these are the distributions behind each figure.
- Time to First Audiop50 201 ms · Max 2979 ms
- TTFA Network Roundtripp50 146 ms · Max 2958 ms
- TTFA Leading Silencep50 52 ms · Max 455 ms
- Flux TTSp50 0.0% · Max 250.0%
| Metric | Average | p25 | p50 | p75 | p90 | p95 | Max | Samples |
|---|---|---|---|---|---|---|---|---|
| Time to First Audio | 218 ms | 173 ms | 201 ms | 232 ms | 294 ms | 391 ms | 2979 ms | 2,378 |
| TTFA Network Roundtrip | 166 ms | 136 ms | 146 ms | 177 ms | 221 ms | 312 ms | 2958 ms | 2,378 |
| TTFA Leading Silence | 53 ms | 36 ms | 52 ms | 64 ms | 73 ms | 78 ms | 455 ms | 2,378 |
| Word Error Rate | 1.8% | 0.0% | 0.0% | 2.6% | 9.1% | 16.7% | 250.0% | 2,328 |
Last 30 days
Daily medians from the same measurement runs · gaps are days without qualifying runs.
How fast is Flux TTS?
On Deepgram, Flux TTS measures mean 218 ms time to first audio (14th of 32). Last measured 2026-11-21.
How accurate is Flux TTS?
On Deepgram, Flux TTS measures 1.8% word error rate (21st of 32). Last measured 2026-11-21.
Who hosts Flux TTS?
Flux TTS is created by Deepgram and served by Deepgram. 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.