Synthesize Text

Allows you to synthesize text into spoken audio and retrieve the synthesized audio stream as an array of bytes.

Endpoint Details

• URL: {{Address}}/v1/speech/synthesis/tts
• HTTP Method: POST
• HTTP Request: POST v1/speech/synthesis/tts
• Summary: Synthesizes text to spoken audio.
• Request: JSON Format.

Query Parameters (Optional)

You have the option to query available voices based on culture and gender using query parameters. For example:

• {{Address}}/v1/speech/synthesis/voices/?language=tr-TR&gender=female

Request Fields Descriptions

Request:

• Text: The text to be synthesized (plain text).
• Name: Speaker name.
• Volume: The base volume (loudness) level of the voice. Range is 0.0-2.0.
• Rate: The speaking rate of the voice. Range is 0.33-3.0.
• Format: Audio output format.
• Sample Rate: Audio output sample rate.
• Authorization: Bearer token for licensing.

Request Examples

Request Example for WAV File:

{
  "Text": "Hello World",
  "Voice": {
    "Name": "Emily",
    "Volume": 1.0,
    "Rate": 1.0
  },
  "Audio": {
    "Format": "wav",
    "FormatDetails": {
      "Encoding": "pcm",
      "SampleRate": "8000"
    }
  }
}

Request Example for Opus File:

{
  "Text": "Hello World",
  "Voice": {
    "Name": "Emily",
    "Volume": 1.0,
    "Rate": 1.0
  },
  "Audio": {
    "Format": "opus",
    "FormatDetails": {
      "BitRateKbps": "8",
      "SampleRate": "8000"
    },
  }

Response

The response returns the audio stream for the specified text as an array of bytes in the specified MIME type: WAV, Opus, MP3, FLV.

Response Codes

Failure Response Example:

{
  "errorCode": "http-404",
  "errorMessage": "Unknown voice name",
  "moreInfo": "",
  "success": false
}