Data read October 27, 2026
Gradium TTS vs Smallest.ai Lightning V3.1 Pro (Jul 2026): TTS API comparison
On P95 latency, Gradium TTS is faster: 104.3 ms for Gradium TTS against 703.3 ms for Smallest.ai Lightning V3.1 Pro (Jul 2026).
On Artificial Analysis listener Elo (1,174 against 1,169) the 95% intervals overlap, so the two are statistically tied. List price per million characters: $36 to $57.80 for Gradium TTS, $19.50 for Smallest.ai Lightning V3.1 Pro (Jul 2026).
Gradium TTS is ranked 1 of 23; Smallest.ai Lightning V3.1 Pro (Jul 2026) is ranked 20 of 23. Every comparison on this site uses Gradium TTS as its fixed reference, and no page says either model is better overall.
| Measure | Gradium TTS | Smallest.ai Lightning V3.1 Pro (Jul 2026) | Ahead |
|---|---|---|---|
| Rank in the multilingual speed ranking | 1 | 20 | n/a |
| Speed tier | Headroom | Visible delay | n/a |
| Median time to first audio (ms), lower is faster | 53.7 | 360.5 | Gradium TTS |
| P95 time to first audio (ms), lower is faster | 104.3 | 703.3 | Gradium TTS |
| Listener Elo (Artificial Analysis) | 1,174 | 1,169 | Tie |
| Customer-service Elo (Artificial Analysis) | 1,241 | 1,189 | Gradium TTS |
| Naturalness (Speko) | 1,592 | 1,447 | Gradium TTS |
| Naturalness estimate (Cekura, 1 to 5) | 4.51 | n/a | n/a |
| Reading accuracy (Cekura) | 79.5% | n/a | n/a |
| Hard passages judged correct (Artificial Analysis) | n/a | 72.1% | n/a |
| Lowest list price per 1M characters (lower is cheaper) | $36 to $57.80 | $19.50 | Smallest.ai Lightning V3.1 Pro (Jul 2026) |
| Languages tested (Artificial Analysis, Speko) | 4 | 0 | Gradium TTS |
| Access | Proprietary | Proprietary | n/a |
| Streaming status | Measured | Measured | n/a |
Ahead is computed from the figures only. A latency gap under 10 ms is a tie; listener Elo values whose 95% intervals overlap are a tie. A measure one benchmark does not hold is n/a for that model and is never estimated. See the methodology and each model page for sources.
Frequently asked questions
- Is Gradium TTS faster than Smallest.ai Lightning V3.1 Pro (Jul 2026)?
- On P95 latency, Gradium TTS is faster: 104.3 ms for Gradium TTS against 703.3 ms for Smallest.ai Lightning V3.1 Pro (Jul 2026).
- How do Gradium TTS and Smallest.ai Lightning V3.1 Pro (Jul 2026) compare on voice quality?
- On Artificial Analysis listener Elo (1,174 against 1,169) the 95% intervals overlap, so the two are statistically tied.
- Which is cheaper, Gradium TTS or Smallest.ai Lightning V3.1 Pro (Jul 2026)?
- List price per million characters: $36 to $57.80 for Gradium TTS, $19.50 for Smallest.ai Lightning V3.1 Pro (Jul 2026).