# Kokoro 82M

Kokoro 82M is an advanced text-to-speech AI model designed to convert written text into natural-sounding voice output.

## API Information

- **Model Slug:** kokoro-82m
- **Branded URL:** https://www.eachlabs.ai/kokoro/kokoro/kokoro-82m
- **Provider:** Kokoro
- **Category:** Text to Voice
- **Output Type:** audio
- **Status:** active
- **Base Cost:** $0.0002475 per processing second
- **Estimated Processing Time:** 1 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/kokoro-82m

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.0002475 per processing second
- **Pricing Details:** default: $0.000247

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| voice | string | No | af | af, af_bella, af_sarah, am_adam, am_michael, bf_emma, bf_isabella, bm_george, bm_lewis, af_nicole, af_sky | An enumeration. |
| speed | number | No | 1 | - | Speech speed multiplier (0.5 = half speed, 2.0 = double speed) |
| text | string | Yes | - | - | Text input (long text is automatically split into smaller chunks) |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kokoro-82m",
  "input": {
    "text": "Hi,  welcome to Eachlabs AI! We are here to help you discover the power of artificial intelligence and provide you with the best experience."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated audio)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**kokoro-82m — Text-to-Voice AI Model**

kokoro-82m from Kokoro delivers compact, high-performance text-to-speech synthesis, converting written text into natural-sounding audio with remarkable efficiency on edge devices. This 82 million parameter model stands out by achieving 1,100 tokens per second inference speed on NVIDIA Jetson T4000 hardware, enabling real-time voice generation where larger TTS systems falter. Developed as part of the kokoro family, kokoro-82m powers developers seeking **kokoro-82m API** integration for low-latency applications like robotics and embedded systems, trained on under 100 hours of audio for multilingual support.

Ideal for users searching for "open source text to speech software" or "best text-to-voice AI model," kokoro-82m prioritizes speed and naturalness in resource-constrained environments, making it a go-to for on-device voice output without cloud dependency.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.