A

Async Pro v1.0 text-to-speech model

asyncReleased May 2026.

Async Pro v1.0 is a text-to-speech (TTS) model from async. It ranks #36 of 103 on the Artificial Analysis TTS arena with Elo 1127 (95% CI ±11, 2,602 samples). List price is about $20.2 per 1M characters. Released May 2026.

Key facts

AA Elo1127±11#36 / 103
TTS Arena Elo–TTS Arena V2
Price (per 1M chars)$20.2USD
ReleasedMay 2026Open weights:–
Provider
async
AA rank
#36 / 103
AA Elo (95% CI)
1127 ±11
AA samples
2,602
Price (per 1M chars)
$20.2
Released
May 2026
Voices tested by AA
8

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: #36 of 103 on Artificial Analysis, in the top half.
  • Mid-range budgets: $20.2 per 1M characters, in the middle third of 83 priced models.
  • Use via async's service or API; the sources do not list it as open weights.
  • Existing async users: this vendor has 4 models on the board.

Nearby models

By AA Elo; this model highlighted
#ModelAA EloArena EloPrice $/1M charsOpen weightsΔ
33Azure HD 2.5 Microsoft1143–$22–+16
34AAsync Flash v1.5 async1139–$10.1–+12
35Step TTS 2 (Mar 2026) StepFun1136–$40–+9
36AAsync Pro v1.0 async1127–$20.2–
37Speech 2.6 HD MiniMax11251494$100–-2
38Speech 2.6 Turbo MiniMax11201510$60–-7
39SSimba 3.0 SpeechifyAI1115–$6.6–-12

Alternatives · Cheaper with AA Elo ≥ 1097

#ModelAA EloArena EloPrice $/1M charsOpen weights
3Qwen-Audio-3.1-TTS-Plus Alibaba1301–$19.3–
5Gemini 3.8 Flash TTS Google1282–$16.5–
8Qwen-Audio-3.0-TTS-Plus Alibaba1266–$19.3–
10Gemini 3.8 Flash-Lite TTS Google1254–$11–
11SSimba 3.2 SpeechifyAI1247–$6.6–

Alternatives · More from async

#ModelAA EloArena EloPrice $/1M charsOpen weights
–ACastleFlow v1.0 async–1547––
34AAsync Flash v1.5 async1139–$10.1–
72AAsync Flash v1.0 async1047–$10.1–

Alternatives · Top 5 open-weight by AA Elo

#ModelAA EloArena EloPrice $/1M charsOpen weights
12Fish Audio Drama 3 Preview Fish Audio1239–$15Open
13BBreeze TTS 2 BreezeBlue1226–$34Open
22Ming-3.0-tts Ant Group1189––Open
42Fish Audio S2 Pro Fish Audio1108–$15Open
46Step Audio EditX (Mar 2026) StepFun1097––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 Async Pro v1.0 rank among TTS models?

As of Nov 7, 2026, Async Pro v1.0 ranks #36 of 103 on the Artificial Analysis TTS leaderboard with Elo 1127 (±11).

Is Async Pro v1.0 open source?

The sources do not list Async Pro v1.0 as open-weight; it is generally used through the async 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 Async Pro v1.0 cost?

According to Artificial Analysis, Async Pro v1.0 costs $20.2 per 1M characters. Prices change; check the vendor for current pricing.

Who makes Async Pro v1.0?

Async Pro v1.0 is made by async; Artificial Analysis lists its release as May 2026.

How reliable is Async Pro v1.0's score?

The scores are based on 2,602 Artificial Analysis samples (95% CI ±11). More samples and narrower intervals mean a more stable rank.

How far is Async Pro v1.0 from #1?

#1 on Artificial Analysis is Eleven v4 (Elo 1334); Async Pro v1.0 has Elo 1127, 207 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.