The only perfect speaker diarization API
1`00% perfect diarization
Diarized transcripts when you need them
Speaker diarized transcripts are available in real-time, using webhooks or after the call with a single call to the API transcription endpoint.
Speaker labels minutes, not months
Works for all plans, on all platforms
Works for your users across video conferencing platforms even if:
- They are not the host of the meeting
- They are on the free plan of a platform
How to get speaker diarized transcripts
Get transcripts with speaker labels using meeting bots (below) or using the Desktop Recording SDK.
Keep your meeting data secure
Just call our Meeting Bot API or use our Desktop Recording SDK and we’ll handle scaling, reliability, and compliance, so your team can focus on creating the features your users love.
Reliable and stable
Onboarding support
Scalable infrastructure
Security controls
For more information, check out our security portal.
Easiest API to get speaker labels
Either create a bot or use a desktop recording SDK to get transcripts with speaker labels from meetings. Recall.ai's perfect diarization means that your app will get diarized transcripts with 100% accurately assigned speaker labels. Unlike other speaker diarization methods, Recall.ai's ability to use speaker separated streams allows Recall.ai to accurately identify what is being said and who is saying it when speakers talk over one another. Other speaker diarization APIs have issues correctly attributing speech in such sitations.
Frequently asked questions
Is the process of identifying who spoke when in a conversation.
The difference between perfect diarization and speaker diarization generally is that perfect diarization tells you who spoke each word of a transcript. Speaker diarization tells you who spoke throughout a conversation, but when speakers speak at the same time, many APIs or products that claim speaker diarization will fail to correctly identify all of the words that were said and who said them.
Yes. Recall.ai offers perfect diarization.
Yes, Recall.ai is SOC 2, ISO 27001:2022, GDPR, CCPA, and HIPAA compliant.
Using Recall.ai's Speaker Diarization API you can receive diarized transcripts in real time or after the conversation.
We can either store your data or you can set custom retention for all of your speaker diarized transcripts depending on your needs and compliance requirements.
You can get diarized transcripts for unlimited simultaneous meetings using Recall.ai's Speaker Diarization API. Recall.ai handles all scaling.
Yes. You can get recordings and transcripts in addition to metadata and speaker names.
Using Recall.ai, most teams get their first diarized transcript in a few minutes using the dashboard or a matter of hours using the docs to use to the Recall.ai API in code.
In the context of labeling audio, there is no difference between a speaker labels API and speaker diarization API. They are used interchangeably.
You can use Recall.ai Transcription or you can bring your own API keys for any of our transcription providers.
