Introducing Audio Perception-1

Audio is one of the largest sources of unstructured data, and most of it is never listened to.

Today, we are excited to launch our first audio understanding model, Audio Perception-1, which is SOTA in emotion detection ahead of OpenAI and Gemini. It takes audio as input and outputs decisions.

Here are results on Besimple’s Vocal Affect Bench.

BeSimple AI Vocal Affect Bench rankings: Hopper Audio Perception-1 leads with 63.2% accuracy, followed by Oruk Resonance 2 at 46.1% and Gemini 3.8 Flash at 45.0%.
Source: BeSimple AI, Vocal Affect Bench. Results published October 28, 2026, on a private evaluation set of 280 recordings. Screenshot captured November 8, 2026.

You can use it in the following ways:

If you're a robotics company

Give your robot ears (real ones):

  • Hear a child crying.
  • Understand pet sounds.
  • Notice footsteps or glass breaking.

If you're a model training company

Use it as a verifier for RL:

  • Score naturalness and emotion.
  • Compare checkpoints without human raters.

If you're a voice agent company

Run it on your call recordings and ask:

  • Did the customer get their task done? Yes/No
  • Did the agent mispronounce any names?
  • How would a human rate this call, 1–10?

Essentially, replace your manual QA of listening to calls.

How did we get here?

One of our customers is a gaming company that wanted us to post-train their TTS model. Their goal was to bring out accents and emotions better than ElevenLabs for NPCs.

We are a startup and didn't want to spend 6 figures on buying the training data. RL with verifiable rewards was our most promising path. Until now, most publicly available TTS research used RL mainly for things like word error rate and talking speed, which are easier to verify.

We looked at the existing LLMs that support audio input, but they are so bad and flaky that we decided to train our own model.

BeSimple AI recall by emotion for Hopper Audio Perception-1: sad 87.5%, neutral 72.5%, happy 60.0%, angry 57.5%, surprised 57.5%, fearful 55.0%, and disgusted 52.5%.
Source: BeSimple AI. Audio Perception-1’s recall across the seven emotion categories in the same evaluation. Screenshot captured November 8, 2026.