Anar Labs
Anar Voice
Calls become searchable text.

Voice turns recorded calls into text, labels dialect and sentiment, and keeps each transcript searchable.

ForCall centre and citizen service leads
DateNovember 2026
The problem
Recorded calls hold answers that nobody can search.
01
Audio is not searchable

A recording cannot be searched for a name, a topic or a complaint.

02
Many dialects

Callers speak Gulf, Egyptian, Levantine and other forms of Arabic.

03
Too many calls to hear

Supervisors cannot listen to every call.

Anar Voice
What it is
Upload a recording. Get a transcript you can search.
01
A recorded call

Upload a file in one of 9 audio formats, up to 25 MB.

→
02
Anar Voice

Sends the audio to a speech service. Then it labels dialect and sentiment on the text.

→
03
The transcript

Voice stores it. Search it and see it in call analytics.

Anar supplies no models. You supply the key for the speech service.

Anar Voice
Transcription
Each call becomes text you can find.
Transcribe

Arabic, English or automatic detection. Nine audio formats, up to 25 MB for each file.

Shipped
History and search

Voice keeps each transcript. Search across all of them.

Shipped
Custom vocabulary

Add names and terms that the speech service must know.

Roadmap
ShippedPartialRoadmap
Anar Voice
Analysis
Labels on each transcript, with limits.
Dialect label

Five classes: Gulf, Egyptian, Levantine, Maghrebi and Modern Standard Arabic. Voice finds marker words in the text.

Partial
Speaker turns

Voice splits the text into turns at pauses and questions. It does not identify voices.

Partial
Sentiment

A word list gives each call a sentiment. Call analytics shows the counts.

Partial

No accuracy figure exists yet for transcripts or labels.

Anar Voice
Speech out
Speech output and the assistant work with limits.
Speech output

Six voices with English names. It needs its own key. Arabic quality is not tested.

Partial
Voice assistant

Audio in, a text answer out. It does not speak the answer.

Partial
Live stream

A WebSocket takes audio chunks. Each chunk gets a full transcription.

Partial
Telephony

Connect Voice to your phone system.

Roadmap
Anar Voice
Status today
What works now, and what does not yet.
CapabilityStatusNote
Transcription, history, searchShippedRecorded files. Not real time.
Dialect, speaker turns, sentimentPartialRules on the text. No accuracy figure.
Speech service endpointPartialFixed in the code. Not through Anar Gateway.
Speech output, voice assistantPartialThe assistant answers in text only.
Access controlPartialOne customer per deployment.
Telephony, personal-data masking, consentRoadmapPlanned. Not built.
Anar Voice
Roadmap
The next steps replace rules with models you choose.
Now
  • Transcription of recorded calls
  • History and search
  • Call analytics
Next Roadmap
  • Better speaker and dialect detection
  • Arabic text preparation for speech output
  • Arabic voices
  • Custom vocabulary
Later Roadmap
  • Mandatory personal-data masking
  • A processing record for each request
  • Real-time streaming and telephony
  • Consent, retention and erasure
  • A published GCC dialect accuracy test
Anar Voice
The platform
Voice uses the Anar platform when you connect it.
Anar Gateway

The voice assistant can send its model call through the gateway. Transcription and speech output do not use it yet.

Anar Guard

Voice can send its events to the Guard audit trail when you set the Guard address.

Anar Voice
Transcribe your own calls with us.

A one-month pilot: we deploy in your environment and run it with one team.

anarlabs.ai/contact

Anar Voice