AssemblyAI-TTS-1 text-to-speech model
AssemblyAI
AssemblyAI-TTS-1 is a text-to-speech (TTS) model from AssemblyAI. It ranks #13 of 99 on the Artificial Analysis TTS arena with Elo 1227 (95% CI ±16, – samples).
Key facts
- Provider
- AssemblyAI
- AA rank
- #13 / 99
- AA Elo (95% CI)
- 1227 ±16
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: #13 of 99 on Artificial Analysis, in the top half.
- Use via AssemblyAI's service or API; the sources do not list it as open weights.
Nearby models
By AA Elo; this model highlighted| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights | Δ |
|---|---|---|---|---|---|---|
| 10 | SSimba 3.2 SpeechifyAI | 1249 | – | $6.6 | – | +22 |
| 11 |  Fish Audio Drama 3 Preview Fish Audio | 1240 | – | $15 | Open | +13 |
| 12 | BBreeze TTS 2 BreezeBlue | 1228 | – | $34 | Open | +1 |
| 13 | AAssemblyAI-TTS-1 AssemblyAI | 1227 | – | – | – | |
| 14 |  Voxtral 3 TTS Mistral | 1223 | – | $13 | – | -4 |
| 15 | IRealtime TTS-2 Flash Inworld | 1217 | – | $10.4 | – | -10 |
| 16 |  v3 Conversational ElevenLabs | 1215 | – | $50 | – | -12 |
Alternatives · Top 5 open-weight by AA Elo
| # | Model | AA Elo | Arena Elo | Price $/1M chars | Open weights |
|---|---|---|---|---|---|
| 11 | Fish Audio Drama 3 Preview Fish Audio | 1240 | – | $15 | Open |
| 12 | BBreeze TTS 2 BreezeBlue | 1228 | – | $34 | Open |
| 23 |  Ming-3.0-tts Ant Group | 1187 | – | – | Open |
| 39 | Fish Audio S2 Pro Fish Audio | 1109 | – | $15 | Open |
| 42 |  Step Audio EditX (Mar 2026) StepFun | 1099 | – | – | 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 AssemblyAI-TTS-1 rank among TTS models?
As of Oct 29, 2026, AssemblyAI-TTS-1 ranks #13 of 99 on the Artificial Analysis TTS leaderboard with Elo 1227 (±16).
Is AssemblyAI-TTS-1 open source?
The sources do not list AssemblyAI-TTS-1 as open-weight; it is generally used through the AssemblyAI API.
Which top-10 TTS model is cheapest?
Among the AA top 10, the lowest list price is Simba 3.2 (SpeechifyAI) at $6.6 per 1M characters, Elo 1249.
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 1240, #11 overall); 18 open-weight models have an AA score.
Who makes AssemblyAI-TTS-1?
AssemblyAI-TTS-1 is made by AssemblyAI.
How far is AssemblyAI-TTS-1 from #1?
#1 on Artificial Analysis is Eleven v4 Turbo (Elo 1336); AssemblyAI-TTS-1 has Elo 1227, 109 points behind.
Sources
17NAS syncs the upstream leaderboards daily; this page's data was synced on Oct 29, 2026.
"–" means the upstream sources do not provide this value; we do not guess.