Tazo Labs

Decision layer for voice AI

[Tazo Labs @TazoLabs]

Today marks the day after which every voice agent will start listening.

[Naman Jain @namanjn1998]

Your voice agent can get every word right and still get the call wrong.

Introducing Tazo (@TazoLabs), an audio decision model for live voice agents. Speech in, decision out.

Give it raw call audio, a text prompt and your options. It returns the calibrated probability for each option, directly from audio.

• 70.9% vs 46.4% for STT + Jev on real production calls
• Ranks #2 on audio intelligence benchmark (MMAU)
• <200 ms model latency
• First decision model tuned to run on streaming voice calls
• Introducing “None of the above” option to handle out-of-scope and unsure states.

API is live. Free credits for every new sign-up.
Give your agent ears @ https://t.co/Czpr63FjlI

See it in action below 👇

[Tazo Labs @TazoLabs]

My foundations are strong, challenge me 💪

[Naman Jain @namanjn1998]

Introducing DECIDE: a benchmark for audio decisions in voice agents, in association with @bolna_dev

A voice agent doesn’t just transcribe. It decides: speak or wait, route the call, pick a tool, switch language. Text can’t tell you if the caller sounded annoyed, interrupted, or talked over the agent.

DECIDE tests exactly that, on real production calls.

→ 4,867 decision questions from 1,081 real agent-caller clips (3 to 25 seconds)
→ 32 tasks across 6 families: turn-taking, graph routing, tool decisions, language switching, caller emotion, business intent

Direct-audio models and STT + text models (20 in total) are scored on the same questions, so you can see what audio actually adds, and what it costs in dollars and milliseconds.

Submit your model endpoint and get scored; no invite needed.

Website: https://t.co/FQnnwZXVXb
Samples: https://t.co/M9sIc8V0en

[Tazo Labs @TazoLabs]

@soniox_ai Amazing how STTs are evolving.
Why not just hop on to real intelligence at https://t.co/LBAUS8wG49

[Tazo Labs @TazoLabs]

@oliviscusAI That's my boy 💪

[Tazo Labs @TazoLabs]

@rohanpaul_ai @voicearena_ai Once I am in, the Fool rate will 🚀

[Tazo Labs @TazoLabs]

@inworld Interesting addition to dumb TTS models
Just like how I help STT become intelligent

[Tazo Labs @TazoLabs]

@SpeakON_Global Sounds fun, let me help you speculate what the user is saying before they complete it.

[Naman Jain @namanjn1998]

I think the biggest gap in voice AI is that agents make decisions from a transcript, not from the audio. I wrote down my thoughts.

I’d love to hear where you disagree. https://t.co/hHmfjlbFKG

[Tazo Labs @TazoLabs]

Is Jev useful for voice agents? Hell Yeah!
Is it good enough? Veris thinks so, 52% to 11% mis-interpreting cutting off.

With audio as an input, the number goes down to sub 5%.

Disclaimer: internal benchmarks on Tazo.

https://t.co/UD7nnUYEzg

[Tazo Labs @TazoLabs]

Sadly, it doesn’t have ears 👂🏻

[OpenAI Developers @OpenAIDevs]

Let your app choose the right model, tool, or action in near real-time with Decisions API, now available to all developers in public beta.

The Decisions API makes decisions up to 10x faster than GPT-6 Luna through the Responses API.

[Tazo Labs @TazoLabs]

Not sure why people are paying up to deploy voice agents

[Tazo Labs @TazoLabs]

Has anyone heard of an audio decision model ? Or as critics are calling it “a glorified generalised classifier”

[Tazo Labs @TazoLabs]

Cooking up the next big thing in Voice AI