Breeze TTS 2 takes the open-weights speech crown by 90 Elo
- Source
- x.com
- Date
Breeze TTS 2 is now the leading Open Weights TTS model in the Artificial Analysis Provider Voices Speech Arena, surpassing Fish Audio S2 Pro by 90 Elo points Breeze TTS 2 is the latest TTS model from @BreezeBlueX, supporting 50 languages, voice generation from text prompts, and streaming generation. Its weights are openly available on Hugging Face. Key takeaways: ➤ Provider Voices: Breeze TTS 2 ranks #1 among Open Weights TTS models, leading the next best Open Weights model, Fish Audio S2 Pro at 1,125, by 90 Elo points. It also ranks #6 overall out of 100+ models, with an Elo of 1,215. ➤ Controlled Voices: Breeze TTS 2 ranks #3 among Open Weights TTS models, with the same Elo as Fish Audio S2 Pro at 1,002. It trails the leading Open Weights model, Mistral's Voxtral TTS, at 1,010 by 8 Elo points, and ranks #16 out of 39 models overall with an Elo of 1,002. ➤ Speed: Breeze TTS 2 processes 45 characters per second, trailing the leading Open Weights model, Fish Audio S2 Pro, at 102 characters per second. ➤ Price: Breeze TTS 2 is priced at $34 per 1M characters on BreezeBlue's hosted endpoint, more expensive than competitor Open Weights model, Fish Audio S2 Pro, at $15 per 1M characters, though weights are also available for self-hosting both models. See more details and listen to samples below ⬇️
On the Controlled Voices leaderboard, Breeze TTS 2 ranks #3 among Open Weights TTS models, with the same Elo as Fish Audio S2 Pro at 1,002. It trails the leading Open Weights model, Mistral's Voxtral TTS, at 1,010 by 8 Elo points, and ranks #16 out of 39 models overall with an Elo of 1,002.
Sample prompt on Breeze TTS 2: “Thanks for your patience. Let me pull up your details now... okay, I can see your parcel left the depot this morning around 6 a.m. and should arrive between 10 and 11 a.m.”
Sample prompt on Breeze TTS 2: “The meal in front of you is approximately 540 calories. Might I suggest adding some of the leftover spinach from last night for a boost of iron today?”
Context
Breeze TTS 2's reported speech-generation lead depends on which voices are compared. In its August 25, 2026 results announcement, Artificial Analysis ranked the open-weights model first among open-weights models and sixth overall in Provider Voices, but third among open-weights models and sixteenth overall in Controlled Voices.
The two boards test different things. Provider Voices has every model speak its own native voices where available, ranked by listener preference in the Speech Arena. Controlled Voices gives every model the same 8 cloned voices. Breeze's first place therefore holds only when each model uses its own voices; with voices held constant, the post puts it level with Fish Audio S2 Pro and 8 Elo points behind Mistral's Voxtral TTS.
Checking sign-in…
Loading comments…