> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://onepin.ai/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://onepin.ai/docs/_mcp/server.

# List Catalog Provider Model Voices

GET https://api.onepin.ai/api/v1/providers/{provider}/models/{model}/voices

List platform voices available for a specific provider and model.

Returns a paginated list of voices from the platform catalog (system
workspace) that declare support for the given `model`. A voice can appear
under multiple models when its `supported_models` list includes more than
one entry; voices with no supported models are excluded from all model
listings.

Voices are restricted to the officially supported locales, judged against THIS
model: a voice whose official locale lives only on a sibling model is not listed
here, and `supported_languages` carries only official locales. A voice for which
the provider supplied no authoritative locale data for this model is excluded too.
The `voice_count` on the model card that links here counts the same population.

Each voice includes gender, age, accent, supported locales, and a short-lived
presigned `preview_url` for the audio sample — do not cache these URLs across
sessions. The response `pagination.total` field reflects the total match count
for the provider/model pair.

For the workspace voice picker (which merges platform and workspace-scoped
voices and supports favorite/similarity filtering), use `GET /voices` with
`?provider=` and `?model=` query parameters instead.

Returns 404 if the provider or model is not recognized or is not available to
your account.

Reference: https://onepin.ai/docs/reference/api-reference/providers/list-catalog-provider-model-voices-api-v-1-providers-provider-models-model-voices-get

## Authentication

- `Authorization` header (bearer token, required) — Clerk JWT token
- `Authorization` header (bearer token, required) — Onepin live API key (`op_live_...`). Test and public keys are reserved in Phase 1.

## Servers

- `https://api.onepin.ai` (prod, default)
- `https://dev-api.onepin.ai` (dev)

## Request

### Path parameters

- `provider` (string, required)
- `model` (string, required)

### Query parameters

- `offset` (integer, optional, default: 0) — Zero-based pagination offset.
- `limit` (integer, optional, default: 20) — Page size (max 100).

### Headers

- `X-Workspace-Id` (string, optional, nullable)

## Response

### 200

Successful Response

- `data` (list of CatalogVoiceOut, required)
- `meta` (Meta, required)
- `pagination` (CountedPaginationMeta, required) — PaginationMeta variant for endpoints that compute an unpaginated total.

## Errors

### 404 Not Found Error

Provider or model not found

- `error` (ApiErrorBody, required)
- `meta` (Meta, required)

### 422 Unprocessable Entity Error

Validation Error

- `detail` (list of ValidationError, optional)

## Types

### CatalogVoiceOut

Lean voice entry for `/providers/{p}/models/{m}/voices`. `provider`/`model` are implied by the path, so they are omitted here. `preview_url` is a short-lived presigned URL for the preview sample.

- `id` (string, required)
- `provider_voice_id` (string, required)
- `name` (string, required)
- `gender` (enum, optional, nullable)
  - Allowed values: `male`, `female`, `neutral`
- `age` (enum, optional, nullable)
  - Allowed values: `young`, `middle_aged`, `old`
- `accent` (enum, optional, nullable)
  - Allowed values: `american`, `british`, `australian`, `indian`, `canadian`, `irish`, `african`, `european`, `east_asian`, `southeast_asian`, `latin_american`, `middle_eastern`, `slavic`, `spanish`, `french`, `german`, `italian`, `portuguese`, `japanese`, `korean`, `chinese`, `thai`, `vietnamese`, `other`
- `supported_languages` (list of string, optional, nullable)
- `preview_url` (string, optional, nullable)
- `emotion_options` (list of string, optional, nullable)

### Meta

- `request_id` (string, required)
- `timestamp` (datetime, required)

### CountedPaginationMeta

PaginationMeta variant for endpoints that compute an unpaginated total.

- `limit` (integer, required)
- `total` (integer, required)
- `next` (string, optional, nullable)
- `prev` (string, optional, nullable)

### ApiErrorBody

- `code` (string, required)
- `message` (string, required)
- `details` (list of ApiErrorDetail, optional, default: [])

### ValidationError

- `loc` (list of ValidationErrorLocItems, required)
- `msg` (string, required)
- `type` (string, required)
- `input` (any, optional)
- `ctx` (ValidationErrorCtx, optional)

### ApiErrorDetail

- `field` (string, required)
- `message` (string, required)
- `line_numbers` (list of integer, optional, nullable)
- `min_chars` (integer, optional, nullable)

### ValidationErrorLocItems

### ValidationErrorCtx

## Examples

**Response**

```json
{
  "data": [
    {
      "id": "string",
      "provider_voice_id": "string",
      "name": "string",
      "gender": "male",
      "age": "young",
      "accent": "american",
      "supported_languages": [
        "string"
      ],
      "preview_url": "string",
      "emotion_options": [
        "string"
      ]
    }
  ],
  "meta": {
    "request_id": "string",
    "timestamp": "2024-01-15T09:30:00Z"
  },
  "pagination": {
    "limit": 1,
    "total": 1,
    "next": "string",
    "prev": "string"
  }
}
```

**SDK Code**

```python
import requests

url = "https://api.onepin.ai/api/v1/providers/provider/models/model/voices"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.onepin.ai/api/v1/providers/provider/models/model/voices';
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.onepin.ai/api/v1/providers/provider/models/model/voices"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.onepin.ai/api/v1/providers/provider/models/model/voices")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("https://api.onepin.ai/api/v1/providers/provider/models/model/voices")
  .header("Authorization", "Bearer <token>")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://api.onepin.ai/api/v1/providers/provider/models/model/voices', [
  'headers' => [
    'Authorization' => 'Bearer <token>',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.onepin.ai/api/v1/providers/provider/models/model/voices");
var request = new RestRequest(Method.GET);
request.AddHeader("Authorization", "Bearer <token>");
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = ["Authorization": "Bearer <token>"]

let request = NSMutableURLRequest(url: NSURL(string: "https://api.onepin.ai/api/v1/providers/provider/models/model/voices")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"
request.allHTTPHeaderFields = headers

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```