Transcription using Recall directly is the most convenient option to start transcribing meetings immediately. You can get started without needing to integrate with any third-party providers.

📘

Recall.ai transcription processes data in the US, regardless of what Region you're using.

Transcription Modes

Real Time Transcription

Real-time transcription with Recall delivers transcripts as the meeting progresses, with two modes to choose from:

Accurate (prioritize_accuracy) - Default

• Use case: Real-time transcription where quality is more important than speed
• Latency: Higher delay but optimized for accuracy (3 - 10 minute delay)
• Accuracy: Best available quality for real-time scenarios
• Features: Full feature support including language detection, key terms, and spelling corrections. See the Create Bot API reference for a full list of supported languages.

Low Latency (prioritize_low_latency)

• Use case: Real-time applications requiring transcripts within seconds of utterance
• Latency: Minimal delay (typically 1-3 seconds)
• Accuracy: Good, but may have more errors than accuracy mode
• Limitations:
  • English only (language_code must be "en")
  • Other configuration parameters currently not supported

Async Transcription

Async transcription takes place after the meeting has already ended. This option can't give you real-time insights while the meeting is still going on, but it is more accurate and feature-rich than real-transcription. It supports all parameters supported by the prioritize_accuracy mode of real-time transcription, namely: language detection, key terms, and spelling corrections.

Quickstart

1. Start an instant meeting and copy the URL.

2. Call Create Bot while setting the transcription_options.provider to recallai.

   Take note of the id in the response.

   
   
   cURL

   curl --request POST \
        --url https://us-east-1.recall.ai/api/v1/bot/ \
        --header 'Authorization: Token {RECALL_API_KEY}' \
        --header 'accept: application/json' \
        --header 'content-type: application/json' \
        --data '
   {
     "meeting_url": {MEETING_URL},
     "transcription_options": {
       "provider": "recallai"
     }
   }
   

3. After the bot joins the call, say a few words or sentences with your mic unmuted.

4. Call Get Bot Transcript with the ID of the bot you created.

   cURL

   curl --request GET \
        --url https://us-east-1.recall.ai/api/v1/bot/{BOT_ID}/transcript/ \
        --header 'Authorization: {RECALL_API_KEY}' \
        --header 'accept: application/json'
   

   a

   JSON

   [
     {
       "words": [
         {
           "text": "No, I am your father.",
           "start_time": 22.65240478515625,
           "end_time": 33.04818725585938,
           "language": null,
           "confidence": null
         }
       ],
       "speaker": "Darth Vader",
   		"speaker_id": 100,
       "language": "en",
     },
     {
       "words": [
         {
           "text": "No, that's not true.",
           "start_time": 38.04785652415625,
           "end_time": 40.85938048518725,
           "language": null,
           "confidence": null
         }
       ],
       "speaker": "Luke Skywalker",
   		"speaker_id": 200,
       "language": "en",
     },
     {
       "words": [
         {
           "text": "That's impossible!",
           "start_time": 42.78515625652404,
           "end_time": 43.72558593804818,
           "language": null,
           "confidence": null
         }
       ],
       "speaker": "Luke Skywalker",
   		"speaker_id": 200,
       "language": "en",
     },
     ...
   ]
   
   

And that's it! You just created your first transcript 🎉

📘

Take it a step further: Webhooks

Since the transcript is being generated in real time, you can also receive webhooks as the meeting transcript is generated.

See Real-Time Transcription Webhooks for more info.

Pricing

Recall.ai transcription costs $0.15 per hour of transcription, for both real-time and asynchronous transcription.

FAQ

Why are my transcripts delayed when using real-time transcription?

When using real-time transcription, the default transcription mode is prioritize_accuracy. Transcripts will be delivered within 3-10 minutes of when the original words were spoken.

What languages are supported by Recall.ai Transcription?

Currently, the following language codes are supported:

auto - auto
bg - bg
ca - ca
cs - cs
da - da
de - de
el - el
en - en
en_au - en_au
en_uk - en_uk
en_us - en_us
es - es
et - et
fi - fi
fr - fr
hi - hi
hu - hu
id - id
it - it
ja - ja
ko - ko
lt - lt
lv - lv
ms - ms
nl - nl
no - no
pl - pl
pt - pt
ro - ro
ru - ru
sk - sk
sv - sv
th - th
tr - tr
uk - uk
vi - vi
zh - zh