You can use Rev as a speech-to-text provider for transcription. This guide explains how to:

Set up Rev as a speech-to-text provider and configure Rev for post-meeting and real-time transcription
Learn how to configure Rev for multilingual transcription and access Rev-specific fields on the transcript data (available when not using Perfect Diarization or Hybrid Diarization)
Covers FAQs

You can use this sample app to compare transcription quality and output across multiple third-party providers using Recall.ai's async transcription API.

Setup

Before using Rev with Recall.ai, you must create a Rev AI access token and add it to the Recall.ai dashboard.

Create a Rev AI access token

Create a new access token in the Rev AI access token page.

Take note of the access token. You will add this token to the Recall.ai transcription dashboard.

Add your Rev AI access token to the Recall.ai transcription dashboard

Add your Rev AI access token in the Recall.ai dashboard for the Recall region where you will create recordings:

❗️
Recall.ai regions are isolated, so you must add your Rev AI access token in each Recall.ai region where you want to use Rev transcription.

Quickstart

Supported transcription workflows

Workflow	Supported
Post-meeting transcription	✅ Yes
Real-time transcription with meeting bots	✅ Yes
Real-time transcription with Desktop Recording SDK	❌ No

Rev for post-meeting transcription

Use post-meeting transcription when you want to transcribe a recording after the recording has completed.

To use Rev for post-meeting transcription, call the Create Async Transcript endpoint and set provider to rev_async along with your preferred Rev transcription options:

curl --request POST \
     --url https://RECALL_REGION.recall.ai/api/v1/recording/RECORDING_ID/create_transcript/ \
     --header "Authorization: RECALL_API_KEY" \
     --header "accept: application/json" \
     --header "content-type: application/json" \
     --data '
{
  "provider": {
    "rev_async": {
      "language": "en"
    }
  }
}
'

See the provider.rev_async field on the Create Async Transcript endpoint for the full list of options available.

📘
See post-meeting transcription for the full post-meeting transcription implementation, including when to create the post-meeting transcript, which webhook events to listen for, how to retrieve the completed transcript, how to handle transcription failures, and more.

Rev for real-time transcription

To use Rev for real-time transcription, set the provider to rev_streaming when creating the recording. Real-time transcript delivery is configured separately through recording_config.realtime_endpoints.

Meeting bots

To use Rev real-time transcription with meeting bots, set recording_config.transcript.provider.rev_streaming in the Create Bot request along with your preferred Rev transcription options:

curl --request POST \
     --url https://RECALL_REGION.recall.ai/api/v1/bot/ \
     --header "Authorization: RECALL_API_KEY" \
     --header "accept: application/json" \
     --header "content-type: application/json" \
     --data '
{
  "meeting_url": "MEETING_URL",
  "recording_config": {
    "transcript": {
      "provider": {
        "rev_streaming": {
          "language": "en"
        }
      }
    },
    "realtime_endpoints": [
      {
        "url": "REAL_TIME_TRANSCRIPT_WEBHOOK_ENDPOINT",
        "type": "webhook",
        "events": ["transcript.data"]
      }
    ]
  }
}
'

See the recording_config.transcript.provider.rev_streaming field on the Create Bot endpoint for the full list of options available.

📘
See Meeting Bot Real-time Transcription for the full meeting bot implementation, including how to create a bot with real-time transcription enabled, configure real-time transcript delivery, subscribe to transcript events, and receive transcript data from a live meeting.

Desktop Recording SDK

Rev is not supported for real-time transcription with the Desktop Recording SDK.

📘
If you are using the Desktop Recording SDK and need real-time transcription, use a real-time transcription provider that supports the Desktop Recording SDK like Recall.ai Transcription, AssemblyAI, Deepgram, or Gladia.

Additional configurations

Multilingual transcription with Rev

In some meetings, participants may speak in more than one language, and you may not know ahead of time which language or languages will be used. In those cases, you can use a transcription provider that supports multilingual transcription. Multilingual transcription generally includes two distinct features:

Feature	Description
Language detection	Detects the spoken language without requiring you to set a language explicitly.
Code-switching	Handles conversations where speakers switch between two or more languages during the same meeting.

Rev supports multiple transcription languages, but language support varies between post-meeting transcription and real-time transcription.

Rev also supports code-switching only for certain language combinations and workflows. For example, Rev supports English/Spanish code-switching for post-meeting transcription using the en/es language code.

Multilingual transcription options for post-meeting transcription

❗️
Rev post-meeting transcription offers limited support for languages and code-switching. Check the language field description in the Rev AI supported languages for the full list of supported language options before enabling code-switching in production.

To configure Rev for post-meeting transcription in a single supported language, set language in the rev_async provider configuration:

{
  // ... other Create Async Transcript request options
  "provider": {
    "rev_async": {
      "language": "es"
    }
  }
}

To configure Rev for English/Spanish code-switching in post-meeting transcription, set language to en/es:

{
  // ... other Create Async Transcript request options
  "provider": {
    "rev_async": {
      "language": "en/es"
    }
  }
}

Multilingual transcription options for real-time transcription

🚧
Rev real-time transcription supports fewer languages than Rev post-meeting transcription and does not support code-switching. Check the language field description in the Rev AI supported languages for the full list of supported language options.

To configure Rev for real-time transcription in a supported language, set language in the rev_streaming provider configuration:

{
  // ... other request options
  "recording_config": {
    // ... other recording options
    "transcript": {
      // ... other transcript options
      "provider": {
        "rev_streaming": {
          "language": "es"
        }
      }
    }
  }
}

Accessing provider-specific fields from Rev transcript data

If you need Rev-specific fields that are not exposed in the normalized Recall transcript, you can access the provider data.

❗️
Provider data is not available when using Perfect Diarization or Hybrid Diarization

Accessing Rev provider data post-meeting

For post-meeting transcription, you can access the raw Rev transcription response from the completed transcript artifact. To access provider data after the meeting, fetch the transcript artifact using the Retrieve Transcript endpoint. Use the data.provider_data_download_url field from the response to download the raw provider response.

The response returned by provider_data_download_url varies by provider. See the accessing provider data section of the post-meeting transcription guide for implementation details.

Accessing Rev provider data in real time

For real-time transcription, subscribe to transcript.provider_data in your real-time endpoint configuration if you need Rev-specific payloads:

{
  "url": "REAL_TIME_TRANSCRIPT_WEBHOOK_ENDPOINT",
  "type": "webhook",
  "events": ["transcript.data", "transcript.provider_data"]
}

See the accessing provider data section of the real-time transcription docs for implementation details.

FAQ

Do I need to add a Rev AI access token in every Recall.ai region?

Yes. Recall.ai regions are isolated, so you must add your Rev AI access token in each Recall.ai region where you want to use Rev transcription.

What regions can I configure with Rev AI?

Recall only supports the US region at this time - Recall does not currently support Rev's EU region.

Can I use Rev for real-time transcription with the Desktop Recording SDK?

No. Rev is not supported for real-time transcription with the Desktop Recording SDK.

You can still use Rev for post-meeting transcription on completed Desktop Recording SDK recordings by creating a post-meeting transcript after the recording has completed.