Deepgram text-to-speech models & pricing
4 models listed · appears on 1 of 3 boards · from $45.00/1M
Speech AI company offering text-to-speech through the Aura and Flux model families, alongside industry-leading speech-to-text.
Models on the boards
Latency from public benchmarks
Time to first audio, in milliseconds, as each benchmark publishes it. We don't measure latency ourselves, and the sources measure differently (harness, region, sample size), so each figure stays under its own source. Not part of the composite score.
None of the latency benchmarks we read lists a Deepgram model yet.
Coval: Time to first audio, p50, us-east-1, read Oct 11, 2026 · Speko: Time to first audio, p50, US East, read Oct 11, 2026 · Humanness Index: Time to first audio, median, read Oct 11, 2026. How latency is sourced.
Recognized models
Not scored — not listed on any of the source boards.