---
title: "Kokoro | Tarka Utilities"
description: "Small, fast TTS — built for low-latency agent loops."
url: "https://tarkahq.com/utilities/kokoro/"
---

Text to speech

# Kokoro

Small, fast TTS — built for low-latency agent loops.

[Sign up](https://tarkahq.com/console?auth=signup) [Utility model docs](https://tarkahq.com/docs/inference/utility-models/)

- **Status**: Live
- **Languages**: English on the current alias
- **License**: Apache 2.0

## Model ID

| Model ID | Designed for |
| --- | --- |
| `kokoro` | Fast English speech with named built-in voices |

Confirm access with `GET /v1/models`, then follow the [utility-model docs](https://tarkahq.com/docs/inference/utility-models/) for the canonical v1 REST or native gRPC request contract.

## Pricing

`kokoro`: Free for a limited time. ~~$0.0001~~ $0.00 per audio second

 USD · catalog 2026-11-04.1. Release verified 2026-11-04. EUR uses the catalog conversion. [Live catalog](https://tarka.rest/control/v1/pricing).

## Overview

Kokoro is a small 82M-parameter Apache 2.0 TTS model. It is a practical choice for responsive English voice output when you do not need voice cloning.

## When to pick Kokoro

- Latency budget is tight (chat-style replies and IVR call legs)
- Throughput is high enough that a compact model is operationally useful
- You do not need voice cloning or emotion control
- English is the dominant language in your workload

## When to pick something else

- **Consent-backed voice cloning** → [Qwen3-TTS](https://tarkahq.com/utilities/qwen3-tts/)
- **Nepali speech with delivery control** → [Nepali Parler TTS](https://tarkahq.com/utilities/nepali-parler-tts/)
- **A lightweight fixed English voice** → [Piper](https://tarkahq.com/utilities/piper/)

Use the `kokoro` alias with `POST /v1/audio/speech` or the native gRPC speech method. Use model discovery and your organization limits as the source of truth for access and request limits.