Artificial Analysis — Text-to-Speech Leaderboard
The neutral, Elo-based TTS leaderboard (the speech analog of an LLM leaderboard), ranking text-to-speech models by blind human preference in a "Speech Arena": listeners compare two samples and vote which sounds more natural. The wiki's anchor for tts-benchmarks. Every number here is a dated snapshot — the board churns weekly.
Top of the board — 2026-10-07 snapshot
| # | Model | Provider | Elo | $/1M chars |
|---|---|---|---|---|
| 1 | Eleven v4 Turbo | ElevenLabs | 1334 | $40.0 |
| 2 | Eleven v4 | ElevenLabs | 1321 | $80.0 |
| 3 | Qwen-Audio-3.1-TTS-Plus | Alibaba | 1292 | $19.3 |
| 4 | Sonic 3.6 | Cartesia | 1278 | $49.0 |
| 5 | gemini 3.8 Flash TTS | 1275 | $16.5 | |
| 6 | Qwen-Audio-3.0-TTS-Plus | Alibaba | 1261 | $19.3 |
| 7 | Realtime TTS-2 | Inworld | 1251 | $20.8 |
| 8 | Simba 3.2 | Speechify | 1242 | $6.6 |
| 9 | gemini 3.8 Flash-Lite TTS | 1242 | $11.0 | |
| 10 | Luna TTS | VUI Labs | 1227 | $15.0 |
Read on 2026-10-07; the page shows no update date, and its newest entries are September 2026 releases. 95 models are ranked, 16 of them open-weight.
The August leader lasted one snapshot. elevenlabs went from tenth (Eleven v3, 1173) to first and second with the v4 pair, and Eleven v4 Turbo at 1334 sits 105 Elo above August's leader. Simba 3.2 is still on the board at eighth, and still the cheapest model in the top ten ($6.6, down from $10). So the August reading that "price and rank have come apart" holds for Simba but not as a law: the new #1 costs $40, mid-table on price.
Scores rose across the board, which makes Elo deltas between snapshots unsafe. Every model present in both snapshots gained: Qwen-Audio-3.0-TTS-Plus 1227 → 1261, Realtime TTS-2 1189 → 1251, Simba 1229 → 1242, Luna 1205 → 1227. A board where nothing loses points is a board whose scale moved, so a model's rank is the comparable number here and its raw Elo is not.
The open-weight picture changed at the top and not underneath. A new open leader, Breeze TTS 2 (BreezeBlue), ranks 11th at 1216, one place outside the top ten and the closest any open model has been. Below it nothing moved up: fish-audio-s2-pro fell from 20th to 33rd (1123 → 1117), kokoro from 48th to 54th (1055 → 1064, a higher score at a lower rank). So "the open field trails" now has one exception and a widening tail.
Top of the board — 2026-08-03 snapshot (all closed/API-only)
| # | Model | Provider | Elo | $/1M chars |
|---|---|---|---|---|
| 1 | Simba 3.2 | Speechify | 1229 | $10.0 |
| 2 | Qwen-Audio-3.0-TTS-Plus | Alibaba | 1227 | $27.6 |
| 3 | gemini 3.1 Flash TTS | 1212 | $18.3 | |
| 4 | Luna TTS | VUI Labs | 1205 | $80.0 |
| 5 | Sonic 3.5 | Cartesia | 1202 | $49.0 |
| 6 | StepAudio 2.5 TTS | StepFun | 1199 | $85.0 |
| 7 | Realtime TTS 1.5 Max | Inworld | 1196 | $26.0 |
| 8 | Lightning V3.1 Pro | Smallest.ai | 1190 | $19.5 |
| 9 | Realtime TTS-2 (research preview) | Inworld | 1189 | $20.8 |
| 10 | Eleven v3 | ElevenLabs | 1173 | $100.0 |
What moved since the 2026-06-05 snapshot
The prior snapshot is kept rather than overwritten, because the movement is the finding.
| Model | Jun 05 | Aug 03 | Δ |
|---|---|---|---|
| Alibaba's leader (Fun-Realtime-TTS → Qwen-Audio-3.0-TTS-Plus) | 1227 (#1) | 1227 (#2) | renamed/relined, same score |
| gemini 3.1 Flash TTS | 1217 (#2) | 1212 (#3) | −5 |
| Sonic 3.5 | 1206 (#4) | 1202 (#5) | −4 |
| Realtime TTS 1.5 Max | 1199 (#5) | 1196 (#7) | −3 |
| Realtime TTS-2 | 1206 (#3) | 1189 (#9) | −17, six places |
A new leader, and it is the one the corpus wrote off. Speechify's Simba tops the board at 1229. Two months ago tts-models-2026-benchmark listed "Speechify SIMBA 3.0" in a trailing clause as the budget option. It is now #1 at $10/1M characters — the cheapest of the entire top ten, against ElevenLabs v3 at $100 for tenth place. Whatever the board is measuring, price and rank have come apart completely at the top.
Also new since June: Luna TTS (VUI Labs) and Smallest.ai's Lightning enter the top ten; StepFun's StepAudio appears as a closed entry at 1199, where June's board had "Step Audio EditX" as the #2 open model at 1112.
Highest open-weight models — and their true rank
| Model | Elo | Board rank | $/1M |
|---|---|---|---|
| fish-audio-s2-pro | 1123 | 20 | $15.0 |
| kokoro 82M v1.0 | 1055 | 48 | $0.7 |
| OpenVoice v2 | 951 | 77 | $8.3 |
The board rank is the number this page failed to record in June, and it changes the picture. Saying "no open-weight model cracks the leaders" understated it: the best open model sits twentieth, and the efficiency favourite sits forty-eighth. Both drifted down over the two months (fish-audio-s2-pro 1128 → 1123, kokoro 1064 → 1055) while the top of the board rose, so the gap to the leader widened from 99 to 106 Elo. See open-weight-tts.
Kokoro's price is listed as $0.7/1M characters here, against the $0.65 this wiki recorded in June — a rounding-level difference, noted rather than resolved.
Method & caveats
Elo from blind A/B votes in the Speech Arena. Reflects perceived naturalness, not WER/latency — pair with the tts-benchmarks page's other axes (CER, MOS, TTFA). Vote populations and sample sets bias results; treat as indicative. Cross-source check: the MarkTechPost survey tts-models-2026-benchmark cites slightly different Elo values (e.g. Gemini 1216 vs 1217 in June) — expected snapshot drift, flagged in synthesis. That article is a fixed 2026-05-30 publication, so its figures are superseded by this snapshot rather than disagreeing with it.
Related
tts-benchmarks · text-to-speech · open-weight-tts · fish-audio-s2-pro · kokoro · tts-models-2026-benchmark