# Tazo Labs: audio-native decision models

> Tazo is an audio-native decision model. It hears the conversation and decides what happens next, no transcript in between.

URL: https://tazolabs.com/

## Speech to Decision. Skip the Transcript.

Tazo Labs builds Tazo, an audio decision model for voice AI. It reads raw call audio and returns a choice between options you define, such as respond, wait, backchannel, yield or escalate, with a calibrated probability for each. It runs as an API next to an existing STT, LLM and TTS stack.

Tazo Labs is the operating name of Kodimo, Inc.

## Use Tazo with an AI agent

To build with Tazo from a coding agent such as Claude Code or Codex, install the Tazo agent skill in the project:

```
npx skills@latest add tazolabs/agent-skills --skill tazo
```

- [Tazo app](https://app.tazolabs.com): sign in, get an API key and try the playground
- [Docs](https://docs.tazolabs.com): documentation for the Tazo API
- [Benchmark](https://benchmark.tazolabs.com/): Tazo's published benchmark results

## FAQs

### What is Tazo?

Tazo is an audio-native decision model. It hears the conversation and decides what happens next, no transcript in between. You define the options, and it returns a calibrated probability for each.

### What is an audio decision model?

An audio decision model listens to audio and picks the next action from a set of options, with a calibrated probability for each. It doesn’t generate text. In a voice agent, it decides when to respond, wait, backchannel, yield or escalate. Tazo is an audio decision model built for live calls.

### How is Tazo different from an LLM?

An LLM generates text one token at a time, and in a voice agent it only runs once the turn is over. Tazo picks from options you define, straight from the audio, and returns a probability for each. Your LLM decides what to say. Tazo decides when, and what happens next.

### Does Tazo need a transcript?

No. Tazo reads raw call audio, so it hears the pitch, pauses and tone that a transcript drops. Those cues are often what tells you whether a caller has finished or is still thinking. [Why the voice AI stack needs a decision model](https://tazolabs.com/blog/voice-ai-decision-models).

### Which decisions can Tazo make?

Any choice you can list: respond or wait, keep talking or yield, backchannel, voicemail, escalate to a human, or start a tool call early. You define the options in the request, so a new decision is a new option list, not a new model. [See the decisions a call needs](https://tazolabs.com/blog/ask-what-the-moment-needs).

### How does Tazo fit into my voice AI stack?

Tazo runs as a standalone API next to your existing STT, LLM and TTS. It reads the same call audio and sends back decisions, so you keep your models, prompts and tools.

### How much does Tazo cost?

We bill per second of audio processed, at $0.20 per hour of audio. You only pay for the audio Tazo listens to. [See the pricing and purchase policy](https://tazolabs.com/policy).

### What are calibrated probabilities, and why do they matter?

A calibrated probability means confidence matches reality: decisions made at 0.9 should be right about nine times in ten. That lets you set a threshold per action, for example escalating to a human only above 0.9.

### How is Tazo different from Jev or AudioJev?

Jev decides from text, so a voice agent has to transcribe the call first. AudioJev answers questions about short audio clips, and its scores aren’t calibrated. Tazo is built for live calls: audio in, calibrated decisions out. [Read the full comparison](https://tazolabs.com/blog/tazo-vs-jev-audio-decision-model).

## Pages

- [Home](https://tazolabs.com/)
- [Manifesto](https://tazolabs.com/manifesto): why Tazo Labs exists
- [Blog](https://tazolabs.com/blog): Research notes, product updates and engineering write-ups from the team building Tazo Labs.
- [Pricing and Purchase Policy](https://tazolabs.com/policy)
- [Terms of Service](https://tazolabs.com/terms)
- [Privacy Policy](https://tazolabs.com/privacy)
- [Plain-text index for AI assistants](https://tazolabs.com/llms.txt)
- Contact: support@tazolabs.com