Hume AI (@hume_ai) header
Hume AI (@hume_ai) profile picture

Build and measure voice models and agents the way people experience them, based on research and grounded in real human judgment.

New York, NY
Joined March 2021
Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)Photo by Hume AI (@hume_ai)
Introducing the Hume Audio Decision API. Ask anything: How many speakers? Is anyone laughing? Is the caller frustrated? What used to take 10+ models is now one call. Trained on 10M+ human judgments, so it answers the way human listeners would. Realtime, or across hours of recordings. Request access below.
215
164
230
1,666
4,700,773
Our team’s so good at optimization, they even cut the time between performance breakthroughs. Two weeks since launch, the Audio Decisions API is faster across the board. Responses now average ~160ms, with 95% back in about 200ms, and our slowest responses are down ~60%. Try it yourself, no account required. 250,000 free tokens (~50 min of audio).
9
5
16
1,013
Sometimes the answer is in the words. Sometimes it’s in the seconds between them. Can Hume’s Audio Decision API detect hesitation? Yeah, I think we’ve got it.
3
3
14
837
A listening test in one API call. We held out one rater at a time and compared how closely the rater and Hume Audio Decision each matched the rest of the crowd. The model came closer in 6 of 7 tests. On four public human-preference benchmarks, it beat 10 other models, including some released just this week. Mean latency: 0.22 s. Full results and methodology below 👇
3
1
13
1,050
Hume AI has been named to CB Insights and Accenture’s NYC Emerging AI 50, which recognizes the most promising AI startups based in New York. We’re listed under AI infrastructure, and that’s exactly where we think voice understanding belongs: underneath the products, helping every system that listens to people go beyond the transcript and actually listen. Thank you to @CBinsights and @Accenture for the recognition, and to the incredible team here whose work earned it.
3
2
1
13
882
Last time, two people. This time, the room gets a lot more crowded. Research engineer Hoon Shin ran our Audio Decision API over another iconic dramatic scene to see how it keeps up with more voices. Each orb is a line of dialogue. Its color shows the emotional mix, its size and pulse show intensity, and a red flare means someone’s raising their voice. With more voices in the scene, the threads have a lot to keep up with while the gauge tracks the tension. All from the audio alone. Not a product, just a glimpse of what this model makes possible.
2
2
1
12
922
Try it yourself. No account required, 250,000 free tokens (~50 min of audio). Click "See a Demo" and start asking questions: hume.ai/products/decision-mo…
1
2
239
You want to know if the Hume Audio Decision API can pick up sarcasm? Wow, what a great question, we've totally never heard that before 🙄 (we're kidding, here's your answer)
4
3
2
17
1,553
Try it yourself. No account required, 250,000 free tokens (~50 min of audio). Click "See a Demo" and start asking questions: hume.ai/products/decision-mo…
1
3
311
The Hume Audio Decision API in 30 seconds, for anyone who missed the launch. Ask it anything about a recording and it answers from the sound itself, not the transcript. A sneeze, a shift in tone, a change of accent. Answers in under a second. One model for every question you have about audio.
21
7
6
68
2,900
Try it yourself. No account required, 250,000 free tokens (~50 min of audio). Click "See a Demo" and start asking questions: hume.ai/products/decision-mo…
3
3
449
Try it yourself. No account required, 250,000 free tokens (~50 min of audio). Click "See a Demo" and start asking questions: hume.ai/products/decision-mo…
156
Experimental demo: Scene Analysis In one of his earliest explorations, research engineer Hoon Shin asked: what happens when our Audio Decision API listens to a scene from a movie? Each orb is a line of dialogue. Its color shows the emotional mix, its size and pulse show intensity, and a red flare means someone’s raising their voice. Threads trace speaker changes, and the gauge tracks tension across the scene, All from the audio alone. Not a product, just a glimpse of what this model makes possible.
20
7
2
39
1,788
Try the Hume Audio Decision API yourself. No account required, 250,000 free tokens (~50 min of audio). Click "see a demo" and start asking questions today: hume.ai/products/decision-mo…
1
4
367
Research engineer Hoon Shin built this liquid metal soundscape with our Audio Decision API. Using the model’s span feature, it picks out and identifies each sound, then renders it as an object morphing in and out of existence. Voices are read for age and language, while laughter and cheers are read for emotion and intensity, and the louder the room gets, the more the sea moves. Not a product, just a glimpse of what this model makes possible. When AI can actually hear, things get a lot more interesting.
9
8
2
41
9,394
For those curious about batch mode: this uncut demo shows the Hume Audio Decision API working through hours of recorded calls, in real time. Reading this post probably took longer than the processing did. All your questions. All your audio. Confidence scores on every answer. Full demo below.
Introducing the Hume Audio Decision API. Ask anything: How many speakers? Is anyone laughing? Is the caller frustrated? What used to take 10+ models is now one call. Trained on 10M+ human judgments, so it answers the way human listeners would. Realtime, or across hours of recordings. Request access below.
7
9
2
36
154,098