Call transcription: the conversation as text

How to turn a call recording into text split into operator and customer lines, which providers are supported and what to do about errors.

Transcription turns a call recording into text laid out as turns: who said what, and when. The text is read in half a minute instead of listening to seven minutes of audio, it can be searched, and it becomes the basis for AI call analysis. This page is about how to get it.

#How to run it

  1. 01

    Open the call

    The Dialogs section → the call you need. The page opens with the audio recording, the call details and the transcription and AI analysis blocks.

  2. 02

    Click “Transcribe”

    The job is queued and processed in the background — you can close the page, the process will not stop.

  3. 03

    Wait for the “Done” state

    While the job is queued it can be cancelled with Cancel transcription. The finished text appears on the same page.

StateWhat it means
NoneTranscription has not been started
QueuedThe job is created and waiting to be processed
ProcessingThe audio has been sent to the model
DoneThe text is saved
CancelledThe job was withdrawn before processing began
FailedIt did not work — details in the errors section below

#What the result looks like

  • The text is split into turns — each one labelled with the speaker (operator or customer) and the time from the start of the call.
  • The first turns are shown by default; the rest expand with the Show more button.
  • The split between speakers relies on the separate recording: the operator’s and the customer’s voices are written to different channels, and the system separates them by channel rather than by ear.
  • A finished transcript can be deleted — the Delete transcription button on the same page.

AI call analysis works on the finished text: it adds marks to individual operator lines and an overall score for the call.

#Providers and settings

The provider is chosen once under Settings → Neural networks. Unless the request says otherwise, the system takes the first one that is enabled and configured — in the order OpenAI → Gemini → x10ai.

ProviderWhat it needsWhen to choose it
OpenAIAn API key; the default transcription model is whisper-1The baseline option: the best recognition of Ukrainian at telephone quality
GeminiA Google API keyIf you already have a Google Cloud account and budget there
x10aiThe address of your own server, a key and a Tenant IDWhen audio must not leave your own perimeter
  • The transcription language is set in the provider settings and defaults to Ukrainian. For mixed Ukrainian-and-Russian conversations leave it at uk — the model copes.
  • The daily-limit fields in the settings are reserved for cost control. For now the budget is better capped on the provider side, with a limit on the key.

#What affects the quality of the text

FactorConsequence
A speakerphone instead of a headsetThe customer’s voice bleeds into the operator’s microphone — the speakers mix and the split into turns breaks down
A noisy roomRecognition swallows word endings, names and addresses
A very short callThree to five seconds often produce no text at all — that is normal
A poor lineDropouts and metallic sound produce invented words, especially in numbers

#Permissions

PermissionWhat it grants
dialogs.viewAccess to the “Dialogs” page and the call card
dialogs.transcribeThe “Transcribe” button
dialogs.listenPlaying the recording alongside the text
dialogs.view_ai_analysisViewing the score and annotations built on the transcript

#Errors and what to do about them

MessageCause and action
“Call recording is missing”The audio was not saved, or the call was made outside the CRM. Check whether a player appears in the lead card
“Transcription is already in progress”A job was created earlier and is still running. Wait for it or cancel it
“OpenAI is not configured or is disabled”There is no key, or the integration is switched off in the “Neural networks” section
The “Failed” stateMost often an invalid key, an exhausted provider balance or a damaged audio file. Try again; if it repeats, check the key
The text is there, but the speakers are swappedThe call was held on a speakerphone or recorded as a single track. The transcript stays readable, but do not build role-based scoring on it

#Checklist

  • The AI provider is connected and marked as configured
  • The transcription language matches the language of your calls
  • A spending limit is set on the provider side
  • The team knows which calls to transcribe rather than doing “all of them”
  • Operators work with headsets, not speakerphones
  • The privacy policy reflects that audio is sent to an external service