whatmodel.sh / tts / Lightning v3.1
Lightning v3.1
↗ share
+ contribute
Lightning v3.1 is a closed-weights text-to-speech model from Smallest.ai, released March 2026. Licence: proprietary.
Catalogue identity notes
Smallest.ai API model lightning_v3.1 (RW-Voice-EQ Appendix Table 4, voice avery, release 2026-03-27). NOT Lightning v3.1 Pro (smallest-lightning-v3-1-pro).
Model information sources
Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.
$ how it compares
The text-to-speech models ranked either side of Lightning v3.1, out of 148 with a score.
| # | model | score | where |
|---|---|---|---|
| 69 |  Chatterbox Multilingual V3 | 54±10 | local |
| 70 |  VibeVoice 1.5B | 53±6 | local |
| 71 | Lightning v3.1 | 53±3 | api $17.50/M chars |
| 72 |  Gepard 1.0 | 53±4 | comparison only |
| 73 |  Kokoro 82M v1.0 | 52±3 | api $0.62/M chars +local |
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests2 not in a task · 96% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot | 1111.5 ✎ | ▁···▁▃··█▄▁▇ beats 3/18 | 88% |
| RW-Voice-EQ TTS · Expressiveness (human) | 3.30 / 5 ✎ | ███···█····█ beats 1/4 | 7.8% |
$ where to run it
Through an API
api · $17.50/M chars · smallest.ai ↗ · price sourceUSD per 1M characters: Smallest.ai lists Lightning v3.1 (not Pro) at approximately $0.175 per 10,000 characters, pay as you go (x100). Product: Lightning text-to-speech API. API model: lightning_v3.1. Settings: pay-as-you-go. Price basis: published (approximate) list rate, per-10K to per-1M scaling only. Exclusions: Lightning v3.1 Pro (~$0.195/10K), enterprise/custom pricing. Currency: USD. Smallest.ai official model pricing page, observed 2026-09-25.
$ how the score was worked out · The Humanness Index by Vapi ·… 88%, RW-Voice-EQ Bench (Hume AI) 8%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 The Humanness Index by Vapi · September 2026 public standings | 1 | 88% |
 RW-Voice-EQ Bench (Hume AI) | 1 | 8% |
| prior · pull toward the middle | 4% | |
| weighted average | = 53.3 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json