Audio

Text-to-speech for long content, voice and voice style (optional).

Request

POSThttps://api.fliki.ai/v1/generate/audio

Headers

{
  "Content-type": "application/json",
  "Authorization": "Bearer API_KEY"
}

Key	Value	Description
Content-Type	application/json	Specifies that the request body format is JSON, allowing the server to parse the data correctly.
Authorization	Bearer YOUR_API_KEY	Generate your API Key in the account/api. section and replace YOUR_API_KEY with your actual key.

Body

{
  "webhook": String,
  "content": String,
  "voiceId": String,
  "voiceStyleId": String | null,
  "playbackRate": Number,
  "format": "mp3" | "wav",
  "pronunciations": Array<{ original: String, replace: String }> | undefined
}

Key	Type	Description	Required	Default
content	string	The content to be converted, typically text. Must not exceed the 10000 character limit.	Yes	N/A
voiceId	string	The identifier for the voice to be used for the output.	Yes	N/A
voiceStyleId	string	The identifier for the style of the voice.	-	N/A
playbackRate	number	The playback rate for the audio. Must be between 0.5 and 2.0.	-	1.0
format	string	The format of the audio file. Must be one of "mp3" or "wav".	-	"mp3"
pronunciations	array	An optional array of objects containing original and replace strings for pronunciation adjustments.	-	N/A
webhook	string	The webhook is a public URL from your server that Fliki will call after your content has been generated. It should be a POST method endpoint to receive responses.	-	N/A

Obtain voiceId and voiceStyleId via the voices endpoint, or copy them from the app. See Finding your IDs.

Response

{
  "fileId": String
}

Key	Type	Description
fileId	string	Unique identifier of the file created

Getting the result

Audio generation is asynchronous. The response above only confirms the job was accepted; it does not contain the audio URL. There are two ways to obtain the finished file:

Poll the status endpoint with the returned fileId:

GET https://api.fliki.ai/v1/generate/status?fileId=<fileId>

Poll every few seconds until status is success, then read the download URL. See Status for the full response shape.

Or use the webhook. If you pass a webhook URL in the request body, Fliki sends a POST to it when the job finishes, so you don't have to poll:

// On success
{
  "success": true,
  "data": {
    "id": String,   // the fileId
    "file": String   // CDN URL of the exported audio
  }
}

// On failure
{
  "success": false,
  "data": {
    "id": String   // the fileId
  }
}

Example

Bash

cURL Request

curl \
  -H "Authorization: Bearer <API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"content": "...", "voiceId": "...", "voiceStyleId": "..."}' \
  -X POST https://api.fliki.ai/v1/generate/audio

TypeScript

TypeScript Request

const apiKey = '<API_KEY>'; // Replace with your actual API key
const url = 'https://api.fliki.ai/v1/generate/audio';

const data = {
content: 'Your text content here',
voiceId: '...',
voiceStyleId: '...',
};

async function generateTextToSpeech(apiKey: string) {
try {
const response = await fetch(url, {
method: 'POST',
headers: {
'Authorization': `Bearer ${apiKey}`,
'Content-Type': 'application/json',
},
body: JSON.stringify(data),
});

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

    const result = await response.json();
    console.log(result);

  } catch (error) {
    console.error('Error generating audio:', error);
  }

}

generateTextToSpeech(apiKey);

Python

Python Request

import requests

api_key = "<API_KEY>"
content = "Your text content here"
voice_id = "..."
voice_style_id = "..."

url = "https://api.fliki.ai/v1/generate/audio"
headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json"
}
data = {
"content": content,
"voiceId": voice_id,
"voiceStyleId": voice_style_id
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Go

Go Request

package main

import (
"bytes"
"encoding/json"
"fmt"
"net/http"
)

func main() {
apiKey := "<API_KEY>"
content := "Your text content here"
voiceID := "..."
voiceStyleID := "..."

  url := "https://api.fliki.ai/v1/generate/audio"
  data := map[string]string{
    "content": content,
    "voiceId": voiceID,
    "voiceStyleId": voiceStyleID,
  }
  jsonData, _ := json.Marshal(data)

  req, err := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
  if err != nil {
    panic(err)
  }

  req.Header.Set("Authorization", "Bearer "+apiKey)
  req.Header.Set("Content-Type", "application/json")

  client := &http.Client{}
  resp, err := client.Do(req)
  if err != nil {
    panic(err)
  }
  defer resp.Body.Close()

  var result map[string]interface{}
  json.NewDecoder(resp.Body).Decode(&result)
  fmt.Println(result)

}