What is the best open-weight text-to-speech model right now?

As of 14 Sep 2026, BreezeBlue Breeze TTS 2 Open Weights is the RightSignal pick for best open-weight TTS (held since 9 Sep 2026). Top open-weight model on the Artificial Analysis provider-voice leaderboard at 1202 Elo, ninth overall and 82 points clear of the next open-weight model, Fish Audio S2 Pro at 1120. BreezeBlue quotes under 40ms time-to-first-audio and a 0.32 RTF on a warmed H100, but those numbers come from the --fast-all path, which wants about 14.4 GiB and a 24GB card; plain eager inference fits in roughly 7.7 GiB, so 12GB is the practical floor. English and Chinese only, and the weights sit under the BreezeBlue Research and Non-Commercial Licence, so commercial self-hosting still needs a separate arrangement.

Pick Best open-weight TTS

BreezeBlue Breeze TTS 2 Open Weights

As of 14 Sep 2026, BreezeBlue Breeze TTS 2 Open Weights is the RightSignal pick for best open-weight TTS.

Top open-weight model on the Artificial Analysis provider-voice leaderboard at 1202 Elo, ninth overall and 82 points clear of the next open-weight model, Fish Audio S2 Pro at 1120.

View on provider site What’s changing

Current pick

since 9 Sep 2026

days as pick

Next best (challenger)

StepFun StepAudio 2.5 TTS (Aug 2026)

Leads the pick 1207 to 1202 on the Artificial Analysis provider-voice board, seventh overall against ninth. It is proprietary and API-only on StepFun's platform at about $85 per 1M characters, though, with no weights published, so it doesn't displace the pick for self-hosters. StepFun's open-weight audio line remains Step-Audio-EditX and Step-Audio-2-mini.

Why it’s the challenger

Reign history

5days
current reign

2challenges
held off

9 SEP 2026became pick

0previous
reigns

Last reviewed: 13 Sep 2026 Reviews are continuous. This pick can change when the evidence changes.

Why BreezeBlue Breeze TTS 2 Open Weights is the pick

Top open-weight model on the Artificial Analysis provider-voice leaderboard at 1202 Elo, ninth overall and 82 points clear of the next open-weight model, Fish Audio S2 Pro at 1120.
BreezeBlue quotes under 40ms time-to-first-audio and a 0.32 RTF on a warmed H100, but those numbers come from the --fast-all path, which wants about 14.4 GiB and a 24GB card; plain eager inference fits in roughly 7.7 GiB, so 12GB is the practical floor.
English and Chinese only, and the weights sit under the BreezeBlue Research and Non-Commercial Licence, so commercial self-hosting still needs a separate arrangement.

Judged on output quality (MOS / arena Elo) · latency · licence · hardware requirements

Evidence

The sources behind this title’s record.

Vendor numbers are treated as claims until independently reproduced — how we judge. Structured benchmark comparisons are on the roadmap.

Caveats & challengers

Open-weight but not open-source: the inference code is Apache-2.0, but the weights, derivatives and self-hosted outputs fall under the BreezeBlue Research and Non-Commercial Licence, and a paid breezeblue.ai subscription only covers outputs from the hosted API — not anything you generate locally.
That keeps Apache-2.0 Step Audio EditX (1099 Elo on the same board) the pragmatic fallback if you need commercial self-hosting.
The lead is also board-specific and language-limited: on Artificial Analysis's controlled-voices arena Breeze ranks third among open-weight models at 1002, behind Mistral's Voxtral TTS at 1010, and the model speaks English and Chinese only.

Challenger StepFun StepAudio 2.5 TTS (Aug 2026)

At a glance

Title: Best open-weight TTS
Licence: Apache-2.0 inference code; weights under BreezeBlue research/non-commercial licence
Pick since: 9 Sep 2026
Last reviewed: 13 Sep 2026
Title holders to date: 8
Official page: huggingface.co/BreezeBlue/Breeze-TTS-2

Title history

Every change, on the record.

View full changelog

Pick 9 Sep 2026 – presentBreezeBlue Breeze TTS 2 Open Weights Current

Top open-weight model on the Artificial Analysis provider-voice leaderboard at 1202 Elo, ninth overall and 82 points clear of the next open-weight model, Fish Audio S2 Pro at 1120.

5 days
as pick

Pick 9 Mar 2026 – 9 Sep 2026Fish Audio S2 Pro

80+ language coverage, fine-grained control and genuinely usable streaming latency; 550k+ downloads say it displaced everything else as t…

184 days
as pick

Pick 12 Nov 2025 – 9 Mar 2026Step-Audio-EditX

Apache-2.0 weights that added iterative post-hoc editing of emotion and style on top of strong zero-shot cloning — the workflow feature p…

117 days
as pick

Pick 28 May 2025 – 12 Nov 2025Chatterbox

The first open model with credible blind-test evidence of beating ElevenLabs (63.75% preference), shipped MIT with emotion-exaggeration c…

168 days
as pick

Pick 26 Dec 2024 – 28 May 2025Kokoro-82M

An 82M-parameter model that sounded better than things twenty times its size and ran on CPU — roughly 12M downloads and the default for a…

153 days
as pick

Pick 7 Oct 2024 – 26 Dec 2024F5-TTS

Flow matching gave noticeably cleaner prosody and faster inference than XTTS; the community moved on quickly despite the non-commercial l…

80 days
as pick

Pick 31 Oct 2023 – 7 Oct 2024XTTS-v2

Made six-second zero-shot voice cloning across 17 languages actually work, and became the workhorse behind most open TTS products for the…

342 days
as pick

Pick 1 Aug 2023 – 31 Oct 2023Bark 91 days
as pick