# Kokoro-82M

> Turn text into natural-sounding speech with 46 voices across 6 languages, billed by compute time at a fraction of a cent per clip.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/hexgrad/kokoro-82m`
- **Model ID**: `hexgrad/kokoro-82m`
- **Category**: sound
- **Kind**: inference
- **Tags**: kokoro, kokoro-82m, hexgrad, text-to-speech, tts, speech-synthesis, multilingual, voice, voice-over, narration, audio, speech

## Pricing

- **Estimated Price**: $0.0000695 average per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/hexgrad/kokoro-82m` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/hexgrad/kokoro-82m/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/hexgrad/kokoro-82m/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/hexgrad/kokoro-82m/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`text`** (`string`, _required_):
  Text to synthesize into speech. Long text is automatically split and synthesized in sequence.

- **`speed`** (`number`, _optional_):
  Speech speed multiplier (0.5 = half speed, 2.0 = double speed).
  - Default: `1`
  - Range: `0.1` to `5`

- **`voice`** (`VoiceEnum`, _optional_):
  Speaker voice. 46 voices across 6 languages, selected by one field: American and British English, French, Hindi, Italian, Japanese, and Mandarin Chinese. The two-letter prefix encodes language and gender (af_/am_ American English, bf_/bm_ British English, ff_ French, hf_/hm_ Hindi, if_/im_ Italian, jf_/jm_ Japanese, zf_/zm_ Mandarin Chinese; f = female, m = male). Pick a voice whose language matches your text.
  - Default: `"af_bella"`
  - Options: `"af_alloy"`, `"af_aoede"`, `"af_bella"`, `"af_jessica"`, `"af_kore"`, `"af_nicole"`, `"af_nova"`, `"af_river"`, `"af_sarah"`, `"af_sky"`, `"am_adam"`, `"am_echo"`, `"am_eric"`, `"am_fenrir"`, `"am_liam"`, `"am_michael"`, `"am_onyx"`, `"am_puck"`, `"bf_alice"`, `"bf_emma"`, `"bf_isabella"`, `"bf_lily"`, `"bm_daniel"`, `"bm_fable"`, `"bm_george"`, `"bm_lewis"`, `"ff_siwis"`, `"hf_alpha"`, `"hf_beta"`, `"hm_omega"`, `"hm_psi"`, `"if_sara"`, `"im_nicola"`, `"jf_alpha"`, `"jf_gongitsune"`, `"jf_nezumi"`, `"jf_tebukuro"`, `"jm_kumo"`, `"zf_xiaobei"`, `"zf_xiaoni"`, `"zf_xiaoxiao"`, `"zf_xiaoyi"`, `"zm_yunjian"`, `"zm_yunxi"`, `"zm_yunxia"`, `"zm_yunyang"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "text": "Bienvenue dans notre nouvelle collection, conçue pour sublimer chaque instant de votre quotidien.",
  "speed": 1,
  "voice": "ff_siwis"
}
```

**Output**

```json
"https://media.modelrunner.ai/xdicu1mk6LdOMwp5OSyTG.wav"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/hexgrad/kokoro-82m \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "text": "Bienvenue dans notre nouvelle collection, conçue pour sublimer chaque instant de votre quotidien.",
  "speed": 1,
  "voice": "ff_siwis"
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("hexgrad/kokoro-82m", {
  input: {
  "text": "Bienvenue dans notre nouvelle collection, conçue pour sublimer chaque instant de votre quotidien.",
  "speed": 1,
  "voice": "ff_siwis"
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "hexgrad/kokoro-82m",
        arguments={
  "text": "Bienvenue dans notre nouvelle collection, conçue pour sublimer chaque instant de votre quotidien.",
  "speed": 1,
  "voice": "ff_siwis"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/hexgrad/kokoro-82m)
- [OpenAPI Schema](https://modelrunner.ai/models/hexgrad/kokoro-82m/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/hexgrad/kokoro-82m/llms.txt)
- [GitHub](https://github.com/hexgrad/kokoro)
- [License](https://www.apache.org/licenses/LICENSE-2.0)
- [Weights](https://huggingface.co/hexgrad/Kokoro-82M)