You are here:
Convert Speech to Text Action
To convert audio files into text, add the Convert speech to text action to a flow.
Required Editions
| View supported editions. |
In Flow Builder, add an Action element to your flow. In the Action field, search for convert speech to text, and select Convert speech to text.
Set Input Values
| Field | Description |
|---|---|
| Content Document ID | 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. |
| Transcription Model | Optional. The transcription model used to convert speech to text. Select Whisper V3 Turbo or ElevenLabs Scribe V2. If you don't select a model, Whisper V3 Turbo is used. |
Store Output Values
| Field | Description |
|---|---|
| Converted Text | The text transcript generated from the audio input. |
Use this action in a Flow to convert an audio file stored in Salesforce to text, and then use the transcript in subsequent Flow elements.
Considerations
- The action is subject to invocation limits per minute. Requests that exceed the limit fail.
- The maximum supported audio file size is 5 MB.
- The action returns the transcript as output and does not store it automatically.
- Processing time can vary based on audio length, file size, audio quality, and system load, as well as the transcription model selected. Whisper V3 Turbo is generally faster, while ElevenLabs Scribe V2 may have less predictable processing times.
- Transcription quality can vary by language. For supported languages, see Generative AI Supported Languages.
Did this article solve your issue?
Let us know so we can improve!
