TTS API comparison 2026
Gradium TTS vs Smallest.ai Lightning v3.1 Gradium vs Smallest.ai · text-to-speech for voice agents
Gradium TTS is in the Headroom speed tier (P95 at or under 101 ms); Smallest.ai Lightning v3.1 is in the no speed tier (not measured by Coval). 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 | Smallest.ai Lightning v3.1 |
|---|---|---|
| Speed tierCoval P95, 30 days | Headroom | not measured |
| Median time to first audioCoval, 30-day window | 55 ms | — |
| P95 time to first audio (slow turns)Coval, 30-day window | 101 ms | — |
| Time to first audio, board chartSpeko, US East | 55 ms | 648 ms |
| Naturalness EloSpeko | 1,592 | 1,544 |
| Listener Elo (95% interval)Artificial Analysis | 1,176 ±13 | 1,022 ±12 |
| Numbers and dates (0 to 1)Speko | 0.27 | 0.25 |
| List price per 1M charactersCoval, Speko, Artificial Analysis | $35.9 to $57.8 | $17.5 to $25 |
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
- →Time to first audio, board chart: 55 ms vs 648 ms (Speko, US East)
- →Naturalness Elo: 1,592 vs 1,544 (Speko)
- →Listener Elo (95% interval): 1,176 ±13 vs 1,022 ±12 (Artificial Analysis)
- →Numbers and dates (0 to 1): 0.27 vs 0.25 (Speko)
Where Smallest.ai Lightning v3.1 is ahead
- →List price per 1M characters: $17.5 to $25 vs $35.9 to $57.8 (Coval, Speko, Artificial Analysis)
Frequently asked questions
- What is the difference between Gradium TTS and Smallest.ai Lightning v3.1?
- Gradium TTS (Gradium) is in the Headroom speed tier (P95 at or under 101 ms); Smallest.ai Lightning v3.1 (Smallest.ai) is in the no speed tier (not measured by Coval). Gradium TTS leads on time to first audio, board chart, naturalness Elo, listener Elo (95% interval) and numbers and dates (0 to 1); Smallest.ai Lightning v3.1 leads on list price per 1M characters. No combined score is computed.
- Which is faster for real-time voice agents, Gradium TTS or Smallest.ai Lightning v3.1?
- Only Gradium TTS is measured by Coval (median 55 ms, P95 101 ms); Smallest.ai Lightning v3.1 has no speed tier, so the two cannot be compared on the same window.
- Which sounds more natural, Gradium TTS or Smallest.ai Lightning v3.1?
- Speko naturalness: 1,592 for Gradium TTS, 1,544 for Smallest.ai Lightning v3.1. Artificial Analysis listener Elo: 1,176 ±13 and 1,022 ±12. 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.