Actions Developer Guide
jNote: This release is in preview. Features described here don’t become generally available until the latest general availability date that Salesforce announces for this release. Before then, and where features are noted as beta, pilot, or developer preview, we can’t guarantee general availability within any particular time frame or at all. Make your purchase decisions only on the basis of generally available products and features.
Speech to Text Action
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}