TTS API comparison 2026
Gradium TTS vs Deepdub Phantom Z 3.4 conversational Gradium vs Deepdub · text-to-speech for voice agents
Gradium TTS is in the Headroom speed tier (P95 at or under 101 ms); Deepdub Phantom Z 3.4 conversational is in the Visible delay speed tier (P95 of 320 ms or more). 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 | Deepdub Phantom Z 3.4 conversational |
|---|---|---|
| Speed tierCoval P95, 30 days | Headroom | Visible delay |
| Median time to first audioCoval, 30-day window | 55 ms | 238 ms |
| P95 time to first audio (slow turns)Coval, 30-day window | 101 ms | 432 ms |
| Time to first audio, board chartSpeko, US East | 55 ms | — |
| Naturalness EloSpeko | 1,592 | not rated |
| Listener Elo (95% interval)Artificial Analysis | 1,176 ±13 | not rated |
| Numbers and dates (0 to 1)Speko | 0.27 | not rated |
| List price per 1M charactersCoval, Speko, Artificial Analysis | $35.9 to $57.8 | not published |
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 238 ms (Coval, 30-day window)
- →P95 time to first audio (slow turns): 101 ms vs 432 ms (Coval, 30-day window)
Where Deepdub Phantom Z 3.4 conversational is ahead
On the published measures, Deepdub Phantom Z 3.4 conversational is ahead of Gradium TTS on none beyond the tie rule. This says nothing about features the benchmarks do not measure.
Deepdub Phantom Z 3.4 conversational: all measurements →Frequently asked questions
- What is the difference between Gradium TTS and Deepdub Phantom Z 3.4 conversational?
- Gradium TTS (Gradium) is in the Headroom speed tier (P95 at or under 101 ms); Deepdub Phantom Z 3.4 conversational (Deepdub) is in the Visible delay speed tier (P95 of 320 ms or more). Gradium TTS leads on median time to first audio and P95 time to first audio (slow turns); Deepdub Phantom Z 3.4 conversational leads on no measure. No combined score is computed.
- Which is faster for real-time voice agents, Gradium TTS or Deepdub Phantom Z 3.4 conversational?
- On Coval's 30-day window read on October 22, 2026, the median time to first audio is 55 ms for Gradium TTS and 238 ms for Deepdub Phantom Z 3.4 conversational (Gradium TTS ahead by 184 ms); the P95, the slow turn, is 101 ms and 432 ms (Gradium TTS ahead by 331 ms). Gaps under 10 ms are ties.
- Which sounds more natural, Gradium TTS or Deepdub Phantom Z 3.4 conversational?
- Speko naturalness: 1,592 for Gradium TTS, not rated for Deepdub Phantom Z 3.4 conversational. Artificial Analysis listener Elo: 1,176 ±13 and not rated. 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.