Skip to main content
All CollectionsDashboardWorkflow Automations
Speech-to-Text Transcription
Speech-to-Text Transcription

Set up a automated transcription and export of call transcripts using workflow automations.

S
Written by Shelby Glynn
Updated over a year ago

This is article overviews a two-part workflow setup: one to automate transcription after a recording has been made, and the second to automate exporting transcriptions via an API request.

User Level:

  • Admin

Speech-to-Text Two Part Setup

Before Starting

In order to access the features needed for this setup, make sure:

  • You've successfully been added to an Expert or Custom plan with CloudTalk

  • CloudTalk Support has enabled Speech-to-Text for your account

Billing for speech-to-text depends on whether you choose to use an enhanced model for transcription, which is an option for some languages. For an enhanced transcription, the rate is 0.072 per minute, while for the default model, the rate is 0.048 per minute.

Adding New Workflows

Workflow automations currently must be accessed through the legacy dashboard.

  1. Navigate to Account > Workflow Automations.

  2. Select + Add Workflow.

1. Transcribe All Calls

Your first workflow automation will cover the transcription part of setup.

Steps

  1. Add a new workflow.

  2. As a trigger, select recording uploaded.

    1. uploaded is the only available Action type for a recording Object.

    2. Note: If no conditions are set, this automation will run for every recording that gets uploaded.

  3. Optional: Add conditions if you want transcribe recordings only in cases where these conditions are met.

  4. Select the Action Speech to Text.

    1. For Key: language, enter the appropriate language reference from the BCP-47 column in Google Cloud's language list.

      1. Note: While we support all languages listed, not all have an Enhanced Phone call model available.

    2. For Key: model, you can choose a specific machine learning model. In most cases, phone_call is best. If having issues, try default.

    3. Set Key: enhancedModel to true to use the advanced phone call model, which optimizes for accuracy.

      1. Supported languages for this option are: English (AU, GB, US), French (CA, FR), German, Italian, Japanese, Portuguese, Russian, and Spanish (US, ES).

      2. Using this model increases the costs of transcription.

  5. When done, select Save and Activate.

2. Export Transcriptions

Your second workflow automation will cover the export part of setup.

  1. Add a new workflow.

  2. As a trigger, select transcription created.

    1. created is the only available Action type for a transcription Object.

    2. Note: If no conditions are set, this automation will run for every transcription that gets created.

  3. Optional: Add conditions if you want export transcriptions only in cases where these conditions are met.

  4. Select the Action API request.

    1. Enter the Endpoint URL. This can usually be located in the API docs or within developer mode of the respective service (unless using a custom application).

      1. Example: https://api.hubapi.com/engagements/v1/engagements (HubSpot engagements)

    2. Method: POST.

  5. In the Values section (the request body), include the following key-value pair:

    1. For Key: transcription, paste the Value:

      {{ event.properties.transcription.csv }}

      1. This is a dynamic value which references the transcription to be exported, converted to a CSV format.

  6. When done, select Save and Activate.

Headers and Values needed to set up the API Request action will vary depending on the requirements of the destination API. Additional entries may include key pairs for token authorizations or content type.

Troubleshooting Tips

  • For information regarding transcription, refer to Google's list of languages, transcription models, and advanced transcription models.

  • In most cases, sending information to another API (such as one associated with a CRM or other internet-connected tool) requires one or more keys or authorization tokens. Ask an admin familiar with the receiving API if you have trouble finding this information.

  • Faulty conditions are often the result of unrecognized inputs in the Property box, or inputs in the Value box which will always result in no matches.

  • After clicking into the Property box, you must click one of the pre-selected keywords within the Useful data for your Workflow section to the right.

  • You can also refer to the Useful data for your Workflow section to validate whether a Value you entered seems to be a good match for a property you've chosen.

Have more questions? Contact our Support team. We're always here to help you!

Related Articles
Automate a Followup SMS
Actions
Send Transcriptions to Slack
Export Voicemail Speech-to-Text
Export Speech-to-Text to HubSpot
Did this answer your question?