Speech to Text Action

Converts speech in an audio file to text using AI-powered speech recognition.

This action is available in API version 66.0 and later.

Supported REST HTTP Methods

URI: /services/data/v66.0/actions/standard/speechToText

Formats: JSON, XML

HTTP Methods: POST

Authentication: Authorization: Bearer token

Inputs

Input	Type	Description
`contentDocumentId`	string	Required. The ID of the audio file stored in Salesforce Files. This value is the contentDocumentId from the ContentDocument object that represents the file to be transcribed.
`transcriptionModel`	string	Optional. The transcription model used to convert speech to text. Valid values are `whisper-v3-turbo` and `elevenlabs-scribe-v2`. If you don’t specify a value, `whisper-v3-turbo` is used.

Outputs

Output	Type	Description
`convertedText`		The transcript of the audio file, returned as plain text in the detected language.

Usage

Sample Input

This sample uses elevenlabs-scribe-v2. You can also set transcriptionModel to whisper-v3-turbo, which is the default if the value isn’t specified.

1{
2    "inputs": [
3        {
4            "contentDocumentId": "069xx000004WhFoAAK",
5            "transcriptionModel": "elevenlabs-scribe-v2"
6        }
7    ]
8}

Sample Output

1{
2    "outputs": [
3         {
4             "convertedText": "Thank you for contacting support. How can I help you today?"
5         }
6    ]
7}