AirCaps AI

Voice AI that hears what other models miss.

[AirCaps AI @tryaircaps]

Introducing A5S Async V1: the world's most accurate speech recognition model for speaker-attributed transcription.

#1 on VoiceArena, ahead of ElevenLabs, AssemblyAI, Deepgram, NVIDIA, Meta & more.

The next-best model makes 41% more errors across 5 public benchmarks.

And yes, every lab says they're #1. So we open-sourced our benchmark.

Try it now👇

[AirCaps AI @tryaircaps]

@glazecl It works quite well with code switching. Try it out on the API! Would love to see if Tape could use our model

[AirCaps AI @tryaircaps]

Introducing A5S Async V1: the world's most accurate speech recognition model for speaker-attributed transcription.

#1 on VoiceArena, ahead of ElevenLabs, AssemblyAI, Deepgram, NVIDIA, Meta & more.

The next-best model makes 41% more errors across 5 public benchmarks.

And yes, every lab says they're #1. So we open-sourced our benchmark.

Try it now👇

[AirCaps AI @tryaircaps]

@FutureGirlAi Thanks! Give it a go on our API…

[AirCaps AI @tryaircaps]

@alvetes17 @ycombinator We have a streaming version of the model in early access for real-time STT (https://t.co/jkGfEmoeud)

[AirCaps AI @tryaircaps]

@Novatechinfo You should give it a spin on the AirCaps API!

[Kanu Gulati | Partner @ Khosla Ventures @KanuGulati]

Blows my mind what a tiny team of AI-pilled engineers can pull off! 🤯

@tryaircaps’ A5S Async v1 ranks #1 on VoiceArena for figuring out who said what. Across their five public benchmarks, the next-best model makes 41% more errors. They’ve open-sourced the benchmark so you can check the results yourself.

Small team. Big swing. Incredible work, @madlavak!

cc @vkhosla @khoslaventures

[Madhav Lavakare @madlavak]

Really excited about this model. The gap between us and previously SOTA STT models like ElevenLabs, Nvidia, AssemblyAI, Google, Meta is surprisingly large. Proud of our tiny team taking on the titans. Try it out on the AirCaps API, first 5h free.

[AirCaps AI @tryaircaps]

@jb_coger Thanks! We want everyone to be able to believe it for themselves...

[AirCaps AI @tryaircaps]

@aikukharenko We've tested across laptop mics, phone mics, conference room mics - it holds up everywhere. And overlap is where you'll see the widest gap between us and others

[AirCaps AI @tryaircaps]

@k1rallik bring on the noise

[AirCaps AI @tryaircaps]

@ConnorWaslo Let's bring voice mode to @try_caddy

[AirCaps AI @tryaircaps]

@brightlinxu Aspect needs to ditch legacy providers and hop on ����

[AirCaps AI @tryaircaps]

@gippp69 Nothing to lose 🤭

[AirCaps AI @tryaircaps]

@knowixbuilds Stress test this on your Netflix show 👀

[AirCaps AI @tryaircaps]

@voicearena_ai 🥳

[Voice Arena @voicearena_ai]

🏆 A new leader on the Voice Arena Diarization + ASR board: AirCaps A5S Async v1 joins the 14 systems already scored and enters at rank #1.

To put this result in context, we evaluated all 15 systems on the same 139 held-out conversations with 2–8 speakers, counting overlapping speech throughout. cpWER measures how accurately a transcript captures words and assigns them to the right speakers.

AirCaps A5S Async v1 scores 23.89% cpWER overall and leads in both settings, with 24.91% cpWER in-person and 17.47% in online calls.

What's particularly interesting is where this lead comes from. AirCaps and Nemotron 3.5 Transcribe (#2) miss a similar share of words (9.29% vs. 8.32%), but AirCaps has a substantially lower substitution rate (10.88% vs. 18.43%) and fewer insertions (3.72% vs. 5.68%).

AirCaps maintains its lead when we resample the 139 conversations. Its overall cpWER showing a 95% confidence interval of 19.47%–28.58%.

Congratulations to the @tryaircaps team on the launch! 👏🏻

[AirCaps AI @tryaircaps]

A5S Async v1 ships with support for 9 languages, key-term prompting, and smart formatting.

Try it in the AirCaps console. Your first 5 hours are free:

https://t.co/sLoPEiEpyo

[AirCaps AI @tryaircaps]

VoiceArena independently tested A5S Async v1 on 139 natural conversations with heavy overlap and up to 8 speakers.

AirCaps ranked #1 of 15 models at 23.88% cpWER, vs. 32.43% for NVIDIA Nemotron 3.5 Transcribe (released a week earlier) and 35.73% for the previous leader, ElevenLabs Scribe v2.