Encoding

The Encoding feature gives users the ability to specify the desired format of the resulting text-to-speech audio output.

📘

The following encoding options are supported for Rest or Streaming.

Enable Feature

To enable Encoding, include the encoding parameter in the query string with the desired encoding option.

Example:

https://api.deepgram.com/v1/speak?encoding=linear16

CURL Examples

You can use the following cURL command in a terminal or your favorite API client to synthesize text into speech with a specific encoding.

Linear16 encoding:

curl --request POST \
     --url "https://api.deepgram.com/v1/speak?model=aura-asteria-en&encoding=linear16" \
     --header "Authorization: Token DEEPGRAM_API_KEY" \
     --header 'Content-Type: application/json' \
     --output outputfile_Linear16.wav \
     --data '{"text": "Hello, how can I help you today?"}'\
     --fail-with-body \
     --silent \
     || (jq . outputfile_Linear16.wav && rm outputfile_Linear16.wav)

MP3 encoding with bitrate of 32 kbits/second:

curl --request POST \
     --url "https://api.deepgram.com/v1/speak?model=aura-asteria-en&encoding=mp3&bit_rate=32000" \
     --header "Authorization: Token DEEPGRAM_API_KEY" \
     --header 'Content-Type: application/json' \
     --output outputfile_mp3_32000.mp3 \
     --data '{"text": "Hello, how can I help you today?"}'  
     --fail-with-body \
     --silent \
     || (jq . outputfile_mp3_32000.mp3 && rm outputfile_mp3_32000.mp3)

Query Parameters

Analyze Response

Upon successful processing of the request, you will receive an audio file containing the synthesized text-to-speech output, along with response headers providing additional information.

📘

The audio file is streamed back to you, so you may begin playback as soon as the first byte arrives. Read the guide Streaming Audio Outputs to learn how to begin playing the stream immediately versus waiting for the entire file to arrive.

Response Headers Example

HTTP/1.1 200 OK
< content-type: audio/mpeg
< dg-model-name: aura-asteria-en
< dg-model-uuid: e4979ab0-8475-4901-9d66-0a562a4949bb
< dg-char-count: 32
< dg-request-id: bf6fc5c7-8f84-479f-b70a-602cf5bf18f3
< transfer-encoding: chunked
< date: Thu, 29 Feb 2024 19:20:48 GMT

📘

To see these response headers when making a CURL request, add -v or --verbose to your request.

This includes:

• content-type: Specifies the media type of the resource, in this case, audio/mpeg, indicating the format of the audio file returned.
• dg-request-id: A unique identifier for the request, useful for debugging and tracking purposes.
• dg-model-uuid: The unique identifier of the model that processed the request.
• dg-char-count: Indicates the number of characters that were in the input text for the text-to-speech process.
• dg-model-name: The name of the model used to process the request.
• transfer-encoding: Specifies the form of encoding used to safely transfer the payload to the recipient.
• date: The date and time the response was sent.

API Error Responses

📘

For information on Deepgram's error messages and error codes, read the API Reference Errors page.