TTS-1 HD text-to-speech model
OpenAIReleased Nov 2023.
TTS-1 HD is a text-to-speech (TTS) model from OpenAI. It ranks #45 of 103 on the Artificial Analysis TTS arena with Elo 1106 (95% CI ±11, 3,787 samples). List price is about $30 per 1M characters. Released Nov 2023.
Key facts
- Provider
- OpenAI
- AA rank
- #45 / 103
- AA Elo (95% CI)
- 1106 ±11
- AA samples
- 3,787
- Price (per 1M chars)
- $30
- Released
- Nov 2023
- Voices tested by AA
- 6
Not yet available: TTS Arena Elo (uncertainty), TTS Arena votes, TTS Arena win rate, Open weights, License, Languages, Voice cloning
Who it is for (from the data)
- Balancing quality and cost: #45 of 103 on Artificial Analysis, in the top half.
- Mid-range budgets: $30 per 1M characters, in the middle third of 83 priced models.
- Use via OpenAI's service or API; the sources do not list it as open weights.
- Existing OpenAI users: this vendor has 3 models on the board.
Nearby models
By AA Elo; this model highlighted| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights | Δ |
|---|---|---|---|---|---|---|
| 42 | 1108 | – | $15 | Open | +2 | |
| 43 | RCoda v2 Rime | 1108 | – | – | – | +2 |
| 44 | 1106 | 1501 | $100 | – | +0 | |
| 45 | 1106 | – | $30 | – | ||
| 46 | 1097 | – | – | Open | -9 | |
| 47 | HSpeech 2.6 Hithink | 1095 | 1485 | – | – | -11 |
| 48 | 1092 | 1493 | $50 | – | -14 |
Alternatives · Cheaper with AA Elo ≥ 1076
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 3 | 1301 | – | $19.3 | – | |
| 5 | 1282 | – | $16.5 | – | |
| 8 | 1266 | – | $19.3 | – | |
| 9 | IRealtime TTS-2 Inworld | 1266 | – | $20.8 | – |
| 10 | 1254 | – | $11 | – |
Alternatives · More from OpenAI
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 52 | 1086 | – | $15 | – | |
| 57 | 1072 | – | $191.6 | – |
Alternatives · Top 5 open-weight by AA Elo
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 12 | 1239 | – | $15 | Open | |
| 13 | BBreeze TTS 2 BreezeBlue | 1226 | – | $34 | Open |
| 22 | 1189 | – | – | Open | |
| 42 | 1108 | – | $15 | Open | |
| 46 | 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 TTS-1 HD rank among TTS models?
As of Nov 7, 2026, TTS-1 HD ranks #45 of 103 on the Artificial Analysis TTS leaderboard with Elo 1106 (±11).
Is TTS-1 HD open source?
The sources do not list TTS-1 HD as open-weight; it is generally used through the OpenAI 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.
How much does TTS-1 HD cost?
According to Artificial Analysis, TTS-1 HD costs $30 per 1M characters. Prices change; check the vendor for current pricing.
Who makes TTS-1 HD?
TTS-1 HD is made by OpenAI; Artificial Analysis lists its release as Nov 2023.
How reliable is TTS-1 HD's score?
The scores are based on 3,787 Artificial Analysis samples (95% CI ±11). More samples and narrower intervals mean a more stable rank.
How far is TTS-1 HD from #1?
#1 on Artificial Analysis is Eleven v4 (Elo 1334); TTS-1 HD has Elo 1106, 228 points behind.
Sources
17NAS syncs the upstream leaderboards daily; this page's data was synced on Nov 7, 2026.
Price and release date come from Artificial Analysis, recorded on Oct 25, 2026.
"–" means the upstream sources do not provide this value; we do not guess.