TTS Callback | Deepgram docs

callback string

Text to Speech Request Text to Speech Stream

Deepgram’s Callback feature allows you to supply a callback URL to which generated text-to-speech audio can be returned. When passed, Deepgram will immediately respond with a request_id before processing your text asynchronously.

Enable Feature

To enable Callback, when you call Deepgram’s API, add a callback parameter in the query string and set it to the URL to which you would like transcriptions sent:

callback=URL

To synthesize text-to-speech and generate an audio file, run the following cURL command in a terminal or your favorite API client:

cURL

curl \
  --request POST \
  --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{"text": "Hello, how can I help you today?"}'
  --url 'https://api.deepgram.com/v1/speak?model=aura-2-thalia-en&callback=URL'

URL Structure

An example URL is https://example.com/callback.

Your callback URLs may reference the http or https protocols.

Authenticating Callback Requests

Authenticate callback requests to confirm that they come from Deepgram. Use Basic Auth: embed username-password credentials in the callback URL in the format https://username:password@example.com. Deepgram includes these credentials when it sends results to your callback server, which can then reject any request without the expected credentials.

Only ports 80, 443, 8080, and 8443 are permitted for callbacks.

Results

When Deepgram has finished analyzing the text, it will send a POST request to the provided callback URL with an appropriate HTTP status code.

If the HTTP status code of the response to the callback POST request is unsuccessful (not 200-299), Deepgram will retry the callback up to 10 times with a 30 second delay between attempts.

Using `CallBack_Method`

To enable the Callback Method, include the callback_method parameter in the query string. By default, the method supports POST, but you can specify PUT instead.