❗️

Provider data is not available by default

Provider data is not available when using Perfect Diarization , Hybrid Diarization, or Recall.ai Transcription, where perfect diairzation is the default diarization method with transcription.

To access provider data, disable perfect/hybrid diarization by setting recording_config.transcript.diarization.use_separate_streams_when_available = false.

Recall returns normalized transcript data across supported speech-to-text providers. In some cases, your application may need fields that are only returned by the underlying speech-to-text provider. To access those fields, use provider data.

Provider data is the raw transcript data returned by the underlying speech-to-text provider.

Use provider data when your application needs provider-specific fields that are not included in Recall.ai's normalized transcript data. For example, you may need provider data if your application uses:

• Provider-specific confidence scores
• Provider-specific word-level fields
• Provider-specific AI features
• Raw response fields from the speech-to-text provider

If Recall.ai's normalized transcript data includes the fields your application needs, you do not need to use provider data.

📘

How to access provider data

Provider data is available differently depending on the transcription workflow you are using.

Transcription workflow	How to access provider data
Post-meeting transcription	Fetch the completed transcript artifact and use the data.provider_data_download_url field to download the raw provider response.
Real-time transcription	Subscribe to the transcript.provider_data event in your real-time endpoint configuration.

Speech-to-text provider-specific field guides

Use the provider guides below to learn how to access provider-specific fields for each supported speech-to-text provider.

🚧

Provider data varies by speech-to-text provider

Provider data is the raw response from the underlying speech-to-text provider. The fields and response shape depend on the provider you use.