TTS API comparison 2026
Gradium TTS vs Deepgram Flux TTS Gradium vs Deepgram · text-to-speech for voice agents
Gradium TTS is in the Headroom speed tier (P95 at or under 101 ms); Deepgram Flux TTS is in the Fast enough speed tier (P95 from 138 ms to 263 ms). Below, each measure side by side with its source; a model leads on a measure only beyond the tie rule. No combined score, no overall winner.
Data read October 22, 2026 · Coval, Speko, Artificial Analysis
Side by side
| Measure | Gradium TTS | Deepgram Flux TTS |
|---|---|---|
| Speed tierCoval P95, 30 days | Headroom | Fast enough |
| Median time to first audioCoval, 30-day window | 55 ms | 200 ms |
| P95 time to first audio (slow turns)Coval, 30-day window | 101 ms | 263 ms |
| Time to first audio, board chartSpeko, US East | 55 ms | 118 ms |
| Naturalness EloSpeko | 1,592 | 1,550 |
| Listener Elo (95% interval)Artificial Analysis | 1,176 ±13 | 1,052 ±13 |
| Numbers and dates (0 to 1)Speko | 0.27 | 0.2 |
| List price per 1M charactersCoval, Speko, Artificial Analysis | $35.9 to $57.8 | $45 |
In bold: the model ahead on that measure. “tie”: latencies within 10 ms, or Elo scores whose 95% intervals overlap.
Where Gradium TTS is ahead
- →Median time to first audio: 55 ms vs 200 ms (Coval, 30-day window)
- →P95 time to first audio (slow turns): 101 ms vs 263 ms (Coval, 30-day window)
- →Time to first audio, board chart: 55 ms vs 118 ms (Speko, US East)
- →Naturalness Elo: 1,592 vs 1,550 (Speko)
- →Listener Elo (95% interval): 1,176 ±13 vs 1,052 ±13 (Artificial Analysis)
- →Numbers and dates (0 to 1): 0.27 vs 0.2 (Speko)
- →List price per 1M characters: $35.9 to $57.8 vs $45 (Coval, Speko, Artificial Analysis)
Where Deepgram Flux TTS is ahead
On the published measures, Deepgram Flux TTS is ahead of Gradium TTS on none beyond the tie rule. This says nothing about features the benchmarks do not measure.
Deepgram Flux TTS: all measurements →Frequently asked questions
- What is the difference between Gradium TTS and Deepgram Flux TTS?
- Gradium TTS (Gradium) is in the Headroom speed tier (P95 at or under 101 ms); Deepgram Flux TTS (Deepgram) is in the Fast enough speed tier (P95 from 138 ms to 263 ms). Gradium TTS leads on median time to first audio, P95 time to first audio (slow turns), time to first audio, board chart, naturalness Elo, listener Elo (95% interval), numbers and dates (0 to 1) and list price per 1M characters; Deepgram Flux TTS leads on no measure. No combined score is computed.
- Which is faster for real-time voice agents, Gradium TTS or Deepgram Flux TTS?
- On Coval's 30-day window read on October 22, 2026, the median time to first audio is 55 ms for Gradium TTS and 200 ms for Deepgram Flux TTS (Gradium TTS ahead by 145 ms); the P95, the slow turn, is 101 ms and 263 ms (Gradium TTS ahead by 162 ms). Gaps under 10 ms are ties.
- Which sounds more natural, Gradium TTS or Deepgram Flux TTS?
- Speko naturalness: 1,592 for Gradium TTS, 1,550 for Deepgram Flux TTS. Artificial Analysis listener Elo: 1,176 ±13 and 1,052 ±13. The two sources use different listeners and can disagree.
- How are these two text-to-speech APIs compared?
- Speed first, on Coval's median and P95 time to first audio; then voice quality (Speko, Artificial Analysis), accuracy on numbers and dates (Speko) and list price. Latencies within 10 ms and Elo scores whose intervals overlap are ties. Scores from different benchmarks are never added into one number.
- Can these numbers be checked?
- Yes. Each model page lists every measurement with its source and the date of the reading, and links to the benchmark page it comes from. The rules are on the methodology page.