> ## Documentation Index
> Fetch the complete documentation index at: https://dialnexa.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# DialNexa Transcripts Recordings And Summaries

> Understand DialNexa transcripts, recordings, realtime transcript, post-call transcript, summary, audio download, and transcript review for Deepgram and Soniox calls.

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.

<Tip>
  Use the transcript for words, the recording for reality, and the summary for speed. Mixing those jobs creates confusion.
</Tip>

## Evidence Type Comparison

| Evidence             | Best for                                                                                                   | Limit                                                                             |
| -------------------- | ---------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- |
| Recording            | Audio quality, tone, interruptions, pauses, pronunciation, and whether the caller actually said something. | Takes time to review.                                                             |
| Realtime transcript  | Understanding what Deepgram or Soniox produced while the agent was deciding what to say.                   | May include recognition errors caused by noise, accents, endpointing, or overlap. |
| Post-call transcript | Cleaner after-call review where available.                                                                 | May not explain the exact live timing that caused an interruption or delay.       |
| Summary              | Fast operational understanding.                                                                            | Not a verbatim record and should not be treated as legal-grade call text.         |

## Realtime Versus Post-Call Transcript

| Question                            | Use realtime transcript              | Use post-call transcript                          |
| ----------------------------------- | ------------------------------------ | ------------------------------------------------- |
| Why did the agent reply too early?  | Yes, because live boundaries matter. | Helpful, but not enough on its own.               |
| Did the caller provide a fact?      | Yes, if the agent acted on it live.  | Yes, for after-call review.                       |
| Why is post-call extraction wrong?  | Useful for raw evidence.             | Often the better text to compare with extraction. |
| Did audio noise affect recognition? | Use with recording.                  | Use with recording.                               |

## Review Speech Quality

<Steps>
  <Step title="Start with recording">
    Listen for noise, overlap, silence, pace, pronunciation, and whether the call path sounds clipped.
  </Step>

  <Step title="Read realtime transcript">
    Check what text the model likely used in the moment.
  </Step>

  <Step title="Compare post-call transcript">
    See whether after-call cleanup changes interpretation.
  </Step>

  <Step title="Use summary last">
    Confirm the summary matches the evidence, not the other way around.
  </Step>

  <Step title="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.
  </Step>
</Steps>

## Transcript And Recording Issues

<AccordionGroup>
  <Accordion title="No recording available">
    The call may not have a recording URL, recording may still be processing, or sensitive data may have been deleted.
  </Accordion>

  <Accordion title="No transcript available">
    The transcript may not exist for that call or may have been removed.
  </Accordion>

  <Accordion title="Realtime transcript differs from post-call transcript">
    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.
  </Accordion>

  <Accordion title="Summary is too thin">
    Improve post-call field definitions, call outcome instructions, or transcript quality before assuming the summary system is broken.
  </Accordion>

  <Accordion title="Transcript has tool noise">
    The copy action filters unhelpful tool-call entries where possible, but review call context before sharing transcripts externally.
  </Accordion>
</AccordionGroup>

## Related Reading

<CardGroup cols={2}>
  <Card title="Speech To Text" icon="file-text" href="/voice-ai/speech-to-text-and-transcription">
    Compare Deepgram, Soniox, and transcript behavior.
  </Card>

  <Card title="Audio Quality" icon="waves" href="/voice-ai/background-noise-denoising-and-audio-quality">
    Diagnose noisy calls.
  </Card>

  <Card title="Call Detail Page" icon="panel-right" href="/monitoring/call-detail-page">
    Use the full detail view.
  </Card>

  <Card title="Annotations" icon="flag" href="/monitoring/annotations-and-call-feedback">
    Mark bad turns.
  </Card>
</CardGroup>
