Skip to main content
DialNexa transcripts, recordings, and summaries help users reconstruct what happened in a call. The recording captures sound, the realtime transcript shows what the agent likely heard during the live conversation, the post-call transcript supports cleaner review where available, and the summary compresses the conversation.
Use the transcript for words, the recording for reality, and the summary for speed. Mixing those jobs creates confusion.

​
Compare DialNexa Transcripts Recordings And Summaries

When no custom summary prompt is configured, DialNexa asks the default summarizer for one factual English paragraph in past tense and third person, with a maximum of 240 words. The summary should preserve specific facts, attribution, actions, and sentiment. If the call contains no caller lines, the default output says that no user messages were received. A custom task_N summary prompt keeps its own instructions instead of using this default. The summary can inherit transcription mistakes. Treat it as a navigation aid, then verify important facts against the transcript and recording. For SIP-routed calls, recordings can be stored as stereo audio. The left channel contains the human caller and the right channel contains the DialNexa agent, for both inbound and outbound directions. Use headphones or a channel-aware audio editor when isolating one side of a SIP audio problem. Other call paths may use a different recording layout, so do not assume every downloaded recording is stereo.

​
Realtime Versus Post-Call Transcript

​
Review Speech Quality

1

Start with recording

Listen for noise, overlap, silence, pace, pronunciation, and whether the call path sounds clipped.
2

Read realtime transcript

Check what text the model likely used in the moment.
3

Compare post-call transcript

See whether after-call cleanup changes interpretation.
4

Use summary last

Confirm the summary matches the evidence, not the other way around.
5

Trace the issue to the right owner

If the text is wrong, tune transcriber or audio. If the text is right but the reply is wrong, tune prompt, model, functions, or variables.

​
Transcript And Recording Issues

The call may not have a recording URL, recording may still be processing, or sensitive data may have been deleted.
Confirm that the player is outputting both stereo channels. Caller audio is on the left and agent audio is on the right. If one channel is genuinely silent, review the SIP media path and Call History evidence.
The transcript may not exist for that call or may have been removed.
That can happen because live transcription optimizes for speed, while post-call processing can be cleaner. Use realtime for live behavior and post-call transcript for review.
Improve post-call field definitions, call outcome instructions, or transcript quality before assuming the summary system is broken.
The copy action filters unhelpful tool-call entries where possible, but review call context before sharing transcripts externally.

Speech To Text

Compare Deepgram, Soniox, and transcript behavior.

Audio Quality

Diagnose noisy calls.

Call Detail Page

Use the full detail view.

Annotations

Mark bad turns.