After I call, I want to get the transcript as quickly as possible Currently I call **vapiClient.stop() **but it can take 20+ seconds for me to get the end-of-call report Is this normal? Is there a way to speed this up to get the transcripts quickly after a call?

Thanks for sharing the details! To help pinpoint the cause of the 20+ second delay, could you let me know which transcription provider and language you’re using in your Vapi configuration? Sources: - [Voice pipeline configuration](https://docs.vapi.ai/customization/voice-pipeline-configuration) - [Server events](https://docs.vapi.ai/server-url/events) - [FAQ](https://docs.vapi.ai/faq)

Deepgram Nova 3, and English

To speed up transcript delivery after calling

vapiClient.stop()

, try reducing the

backoffSeconds

in your stop speaking plan. This parameter controls the recovery "quiet period" after interruptions and can impact how quickly the pipeline finalizes and delivers transcripts. For example:

json
"stopSpeakingPlan": {
  "numWords": 0,
  "voiceSeconds": 0.2,
  "backoffSeconds": 0.5
}

Lowering

backoffSeconds

(e.g., to 0.5) can help the system process and return the transcript more quickly after the call ends. For more details, see the [voice pipeline configuration documentation](https://docs.vapi.ai/customization/voice-pipeline-configuration). Sources: - [Voice pipeline configuration](https://docs.vapi.ai/customization/voice-pipeline-configuration) - [FAQ](https://docs.vapi.ai/faq)

Doesnt seem right - how does backoffseconds help with the end of call report? Could I get more assistance please?

Hey! To help track down this issue, could you share: \- The call ID \- When exactly this happened (the timestamp) \- What response you expected to get \- What response you actually got instead This would really help us figure out what went wrong!