# Matxa Multispeaker Catalan Central Endpoint

**Input parameters**

| Parameter     | Description                                                                                         | Type   | Options/Range                   | Recommended Values |
| ------------- | --------------------------------------------------------------------------------------------------- | ------ | ------------------------------- | ------------------ |
| text          | Input text to be converted to speech                                                                | string | Any text input                  | N/A                |
| voice         | Speaker ID for voice output                                                                         | int    | 47 different speakers available | N/A                |
| temperature   | Controls sampling variance during inference. Lower values yield higher quality but less variability | float  | 0.2 to 0.67                     | 0.2 to 0.67        |
| length\_scale | Related to speech speed. Higher values make the speech slower, while lower values make it faster    | float  | 0.75 to 0.9                     | 0.75 to 0.9        |

Each integer value is associated with one of the speakers you see in the list below. All names starting with “caf\_XXXXX” (female) and “cam\_XXXXX” (male) belong to speakers in the [OpenSLR69](https://huggingface.co/datasets/projecte-aina/openslr-slr69-ca-trimmed-denoised) dataset and short Catalan names in the [festcat](https://huggingface.co/datasets/projecte-aina/festcat_trimmed_denoisedfestcat) dataset.

```json
"cam_03115": 0,
  "caf_04247": 1,
  "caf_05450": 2,
  "cam_08935": 3,
  "caf_09901": 4,
  "ona": 5,
  "pol": 6,
  "cam_02689": 7,
  "caf_06042": 8,
  "jan": 9,
  "caf_08106": 10,
  "cam_04910": 11,
  "cam_08664": 12,
  "caf_07803": 13,
  "cam_06582": 14,
  "caf_06311": 15,
  "caf_07245": 16,
  "cam_06279": 17,
  "caf_09598": 18,
  "caf_09796": 19,
  "eva": 20,
  "cam_00762": 21,
  "caf_09204": 22,
  "caf_03944": 23,
  "caf_05147": 24,
  "uri": 25,
  "mar": 26,
  "cam_00459": 27,
  "teo": 28,
  "caf_03655": 29,
  "bet": 30,
  "cam_06705": 31,
  "caf_05739": 32,
  "caf_06008": 33,
  "cam_04484": 34,
  "cam_03386": 35,
  "cam_08967": 36,
  "caf_06942": 37,
  "cam_07140": 38,
  "pau": 39,
  "caf_08001": 40,
  "pep": 41,
  "cam_04787": 42,
  "eli": 43,
  "caf_01591": 44,
  "caf_02452": 45,
  "cam_02992": 46
```

### Code examples

**Python**

{% code title="example.py" %}

```python
import requests

API_URL = "https://x6g02u4lkf25gcjo.us-east-1.aws.endpoints.huggingface.cloud/api/tts"
headers = {
   "Authorization": "Bearer <hf_token>",
}

def query(text):
   data = {"text": text, "voice": 20}
   return requests.post(API_URL, headers=headers, json=data)

response = query("Bon dia")
with open("output.wav", "wb") as f:
   f.write(response.content)
```

{% endcode %}

**Curl**

Please take into account the apostrophes. An effective way is to create a temporary JSON file to pass text and input parameters for inference.

{% code title="bash" %}

```bash
printf '%s' '{
  "text": "L'\''Aina ha preparat aquest model de síntesi de veu.",
  "voice": 39,
  "type": "text"
}' > data.json

curl -X POST https://x6g02u4lkf25gcjo.us-east-1.aws.endpoints.huggingface.cloud/api/tts -H "Content-Type: application/json" -H "Authorization: Bearer <hf_token>" -d @data.json | play -t wav -

rm data.json// Some code
```

{% endcode %}

**Javascript**

Executed with Node.js. Install NPM (Node Package Manager) and with NPM install fetch-node library.

{% code title="example.js" %}

```javascript
const fetch = require("node-fetch");
const fs = require("fs");

// Define the API URL and headers
const API_URL = "https://x6g02u4lkf25gcjo.us-east-1.aws.endpoints.huggingface.cloud/api/tts";
const headers = {
    "Authorization": "Bearer <hf_token>",
    "Content-Type": "application/json"
};

// Function to send the request
async function query(text) {
    const data = {
        text: text,
        voice: 20,
    };

    try {
        // POST request
        const response = await fetch(API_URL, {
            method: "POST",
            headers: headers,
            body: JSON.stringify(data)
        });

        // Check the response
        if (!response.ok) {
            throw new Error(`Error: ${response.status} ${response.statusText}`);
        }

        // Convert the response to a buffer
        const buffer = await response.buffer();

        // Write the buffer to an output file
        fs.writeFile("output.wav", buffer, (err) => {
            if (err) {
                console.error("Error saving the file:", err);
            } else {
                console.log("File saved as output.wav");
            }
        });

        
    } catch (error) {
        console.error("Error making request:", error);
    }
}

// Example usage
query("Bon dia.");

```

{% endcode %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://langtech-bsc.gitbook.io/aina-kit/aina-hack/text-to-speech/matxa-multispeaker-catalan-central-endpoint.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.