🚧
Important: This guide only applies to workspaces with v1.10 API access
The v1.10 API is only available to Recall accounts created before May 28, 2025.
Do not use this documentation unless the workspace has access to the v1.10 API. If the workspace creation date is unknown, stop and clarify. All other workspaces must use the v1.11 API documentation instead.

🚧
Google Cloud Speech-to-Text is only available for Asynchronous Transcription - not Real-Time Transcription.

Requirements

To use Google Cloud STT with Recall, you will need to provide three things:

A google cloud project with the Speech-to-text API enabled
A service account with a key (.json)
A Google Cloud Storage bucket that the service account can access.

Quick-Start

Follow this video to quickly set up all the credentials:

Setup

Create a google cloud service account
- Make sure the service account's project allows creating service account keys.
- Make sure to add roles/speech.client (Cloud Speech Client) as a role on the account.
- Create a service account key (.JSON) for the service account you just created.
Create a google cloud bucket and add the service account you created above as a principal.
- Recall will upload & delete the files as transcription requests are created & completed; files will not be re-read.
Once you have both the key and the google cloud bucket, add both in the transcription section of the Explorer Dashboard:

Example async transcription request

curl --request POST \
     --url https://us-west-2.recall.ai/api/v2beta/bot/{BOT_ID}/analyze \
     --header "Authorization: $RECALLAI_API_KEY" \
     --header "accept: application/json" \
     --header "content-type: application/json" \
     --data '{
    "google_speech_v2_async_transcription": {
      // This is the default:
      // "recognizer": "projects/{service_account_project}/locations/global/recognizers/_",
      "config": {
        "model": "long",
        "languageCodes": ["en-US"]
      }
    }
  }
'