Phonon 31M (English) text-to-speech model
Gradium
Phonon 31M (English) is a text-to-speech (TTS) model from Gradium. It ranks #40 of 103 on the Artificial Analysis TTS arena with Elo 1111 (95% CI ±14, – samples).
Key facts
- Provider
- Gradium
- AA rank
- #40 / 103
- AA Elo (95% CI)
- 1111 ±14
Not yet available: AA samples, TTS Arena Elo (uncertainty), TTS Arena votes, TTS Arena win rate, Price (per 1M chars), Released, Open weights, License, Voices tested by AA, Languages, Voice cloning
Who it is for (from the data)
- Balancing quality and cost: #40 of 103 on Artificial Analysis, in the top half.
- Use via Gradium's service or API; the sources do not list it as open weights.
- Existing Gradium users: this vendor has 6 models on the board.
Nearby models
By AA Elo; this model highlighted| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights | Δ |
|---|---|---|---|---|---|---|
| 37 |  Speech 2.6 HD MiniMax | 1125 | 1494 | $100 | – | +14 |
| 38 | Speech 2.6 Turbo MiniMax | 1120 | 1511 | $60 | – | +9 |
| 39 | SSimba 3.0 SpeechifyAI | 1115 | – | $6.6 | – | +4 |
| 40 | GPhonon 31M (English) Gradium | 1111 | – | – | – | |
| 41 | RChatterbox HD Resemble AI | 1108 | – | $40 | – | -3 |
| 42 |  Fish Audio S2 Pro Fish Audio | 1108 | – | $15 | Open | -3 |
| 43 | RCoda v2 Rime | 1108 | – | – | – | -3 |
Alternatives · More from Gradium
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| – | GGradium TTS 2026.10 Gradium | – | 1586 | – | – |
| – | GGradium TTS (pre-2026.08) Gradium | – | 1515 | – | – |
| 27 | GGradium TTS (Sep 2026) Gradium | 1172 | – | $47.8 | – |
| 28 | GGradium TTS (Oct 2026) Gradium | 1166 | – | – | – |
| 31 | GGradium TTS (Aug 2026) Gradium | 1151 | – | $47.2 | – |
Alternatives · Top 5 open-weight by AA Elo
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 12 | Fish Audio Drama 3 Preview Fish Audio | 1239 | – | $15 | Open |
| 13 | BBreeze TTS 2 BreezeBlue | 1226 | – | $34 | Open |
| 22 |  Ming-3.0-tts Ant Group | 1189 | – | – | Open |
| 42 | Fish Audio S2 Pro Fish Audio | 1108 | – | $15 | Open |
| 46 |  Step Audio EditX (Mar 2026) StepFun | 1097 | – | – | Open |
How to read the scores
- AA Elo: the Elo score from the Artificial Analysis speech arena. Listeners blind-compare two clips and pick the better one; "±" is the 95% confidence interval.
- TTS Arena Elo: Elo from TTS Arena V2 community blind votes. The two boards use different scales, so do not subtract one from the other.
- If the gap between two models is smaller than their combined intervals, the order is not statistically reliable; treat them as the same tier. More samples or votes mean narrower intervals.
FAQ
Where does Phonon 31M (English) rank among TTS models?
As of Nov 3, 2026, Phonon 31M (English) ranks #40 of 103 on the Artificial Analysis TTS leaderboard with Elo 1111 (±14).
Is Phonon 31M (English) open source?
The sources do not list Phonon 31M (English) as open-weight; it is generally used through the Gradium API.
Which top-10 TTS model is cheapest?
Among the AA top 10, the lowest list price is Gemini 3.8 Flash-Lite TTS (Google) at $11 per 1M characters, Elo 1254.
What is the best open-source TTS model?
By AA Elo, the top open-weight model is Fish Audio Drama 3 Preview by Fish Audio (Elo 1239, #12 overall); 18 open-weight models have an AA score.
Who makes Phonon 31M (English)?
Phonon 31M (English) is made by Gradium.
How far is Phonon 31M (English) from #1?
#1 on Artificial Analysis is Eleven v4 (Elo 1334); Phonon 31M (English) has Elo 1111, 223 points behind.
Sources
17NAS syncs the upstream leaderboards daily; this page's data was synced on Nov 3, 2026.
"–" means the upstream sources do not provide this value; we do not guess.