Are Closed Captions and Real-Time Transcription Billed Separately or Together?

Question

Are Closed Captions and Real-Time Transcription Billed Separately or Together?

Daniel Li 20

I'm asking because I've noticed that these two features seem very similar in both functionality and outputs.

If Closed Captions and real-time transcription are enabled simultaneously on the same Azure Communication Service meeting, will Azure charge twice, or is the speech recognition billed only once?

Do Closed Captions and real-time transcription share the same Speech-to-Text session, or are they metered separately?

Why is there a cost difference between the two features?

I noticed that we only receive the final outputs for real-time transcription, while Closed Captions provide partial outputs and final outputs. Is it possible to also get partial outputs for real-time transcription?

ref: https://learn.microsoft.com/en-us/azure/communication-services/how-tos/call-automation/real-time-transcription-tutorial?pivots=programming-language-csharp

https://learn.microsoft.com/en-us/azure/communication-services/concepts/voice-video-calling/closed-captions

Service	Price
Closed Captions	$0.021/min ($1.26/hour)
Standard Transcription	Real-time Transcription: $1 per hour

Vimal Lalani 2,725 Reputation points Microsoft External Staff Moderator

2025-12-24T22:41:54.81+00:00

Hi @Daniel Li

In Azure Communication Services, Closed Captions and Real-Time Transcription are treated as two separate features and are billed independently, even when they are enabled at the same time in the same meeting. Closed Captions are billed per minute, while Real-Time Transcription is billed per hour, so enabling both will result in charges for both. Although they use the same underlying speech recognition technology, Azure meters them separately for billing purposes.

The pricing difference is due to how the features work. Closed Captions provide live, on-screen text with both partial (interim) and final results, which requires continuous real-time processing. Real-Time Transcription, on the other hand, only produces final transcription results and does not support partial outputs. If partial text updates are required, Closed Captions is the supported option today.

Hope this helps!
Vimal Lalani 2,725 Reputation points Microsoft External Staff Moderator

2025-12-26T01:00:31.8+00:00

Hi @Daniel Li

Following up to check whether the above information was helpful. Feel free to let us know if you need any additional support.

Your answer

Vimal Lalani 2,725 Reputation points Microsoft External Staff Moderator

2025-12-24T22:41:54.81+00:00

Hi @Daniel Li

In Azure Communication Services, Closed Captions and Real-Time Transcription are treated as two separate features and are billed independently, even when they are enabled at the same time in the same meeting. Closed Captions are billed per minute, while Real-Time Transcription is billed per hour, so enabling both will result in charges for both. Although they use the same underlying speech recognition technology, Azure meters them separately for billing purposes.

The pricing difference is due to how the features work. Closed Captions provide live, on-screen text with both partial (interim) and final results, which requires continuous real-time processing. Real-Time Transcription, on the other hand, only produces final transcription results and does not support partial outputs. If partial text updates are required, Closed Captions is the supported option today.

Hope this helps!
Vimal Lalani 2,725 Reputation points Microsoft External Staff Moderator

2025-12-26T01:00:31.8+00:00

Hi @Daniel Li

Following up to check whether the above information was helpful. Feel free to let us know if you need any additional support.

Share via

Are Closed Captions and Real-Time Transcription Billed Separately or Together?

Your answer