Arabic dialects.
Every word, timed.

An Arabic speech-to-text API that doesn’t rewrite the dialect into formal Arabic. Get word-level timestamps, speaker labels, JSON, and SRT for captions and searchable transcripts.

Get an API key Read the API guide

Starting at 1,250 minutes for USD 5.00 /month. Word timestamps, speaker labels, JSON, and SRT included.

Request

export KALEMIO_API_BASE='https://kalemio.app'
export KALEMIO_API_KEY='YOUR_API_KEY'

curl "$KALEMIO_API_BASE/v1/transcriptions" \
  -H "Authorization: Bearer $KALEMIO_API_KEY" \
  -H "Idempotency-Key: conversation-001" \
  -F 'file=@conversation.m4a' \
  -F 'speakers=auto'

Response202 Accepted

{ "id": "tr_5d0c3f6a8e2b4c71a9f0e6d2b8c4a1f3",
  "status": "queued", "duration_seconds": 1.92,
  "billed_seconds": 0, "billed_minutes": 0,
  "reserved_seconds": 2, "billing_method": "credits",
  "processing": "priority",
  "expires_at": "2026-10-01T09:30:00.000Z" }

Asynchronous: the job ID comes back at once. Poll GET /v1/transcriptions/{id} until "status" is "completed", then download /result as JSON or /srt. Complete quickstart script

Completed result

A little Levantine Arabic

أهلاً، كيف فيني ساعدك؟

“Hello, how can I help you?”

أهلاً،0.24–0.68
كيف0.72–0.94
فيني0.98–1.22
ساعدك؟1.26–1.78

{ "text": "أهلاً، كيف فيني ساعدك؟",
  "words": [
    {"text":"أهلاً،","start":0.24,"end":0.68,"speaker_id":"speaker_0"},
    {"text":"كيف","start":0.72,"end":0.94,"speaker_id":"speaker_0"},
    {"text":"فيني","start":0.98,"end":1.22,"speaker_id":"speaker_0"},
    {"text":"ساعدك؟","start":1.26,"end":1.78,"speaker_id":"speaker_0"}
  ],
  "duration_seconds": 1.92 }

1
00:00:00,240 --> 00:00:01,780
[speaker_0] أهلاً، كيف فيني ساعدك؟

Illustrative transcript. Times are in seconds.

The words matter. So does the dialect.

Interviews, podcasts and everyday conversations don’t sound like a textbook. Kalemio is built for Modern Standard Arabic and spoken dialects, keeping the words as they were said.

In our September 2026 benchmark on 2.06 hours of Levantine Arabic, Kalemio had the lowest dialect-tolerant word error rate of the 6 systems tested: 4.6%. Every system got the same audio and the same scoring.

Explore word-level timestamps

Fewer transcription errors.

Dialect-tolerant word error rateLower is better

Kalemio4.6%
Meta Muse Voice 1.06.3%
Hamsa General V27.4%
ElevenLabs Scribe v27.4%
Groq Whisper large-v317.0%
Groq Whisper turbo25.1%

Kalemio benchmark · September 2026 · 2.06 hours of Levantine audio. Same audio and scoring for every model, with spelling and equivalent word forms normalized. Results vary by recording.

Choose your monthly minutes.

The same transcription features on every plan. Start free to evaluate; paid plans get priority, faster processing.

Currency

Plan	Minutes	Price
FreeSlower, queued processing	60 per month	USD 0.00 / month	Start free
Starter	1,250 per month	USD 5.00 / month	Choose Starter
StarterBilled yearly	1,250 per month	USD 50.00 / year	Choose Starter annual
Studio	5,000 per month	USD 13.93 / month	Choose Studio
StudioBilled yearly	5,000 per month	USD 159.00 / year	Choose Studio annual
Top-up	500 extra minutes	USD 5.00 one time	For subscribers. These minutes never expire, even if you cancel your plan.

Free plan: 60 minutes a month, no card needed, with slower, queued processing on a best-effort basis. Jobs are typically several times slower than on paid plans and may wait in a queue. Meant for evaluation, one job at a time. Paid jobs are processed separately with priority and never wait behind the free queue.

Plans renew monthly or yearly until cancelled. Minutes reset every month, on annual plans too, and don’t roll over. Upgrade or cancel from your account.

Prefer no monthly allowance? Optional usage-based billing costs US$0.015 per minute, more than any plan, with a 2-minute minimum (US$0.03) per job. How plans and usage-based billing compare

Send the audio. Or the video.

Formats: MP3, M4A, PCM WAV, MP4 and MOV. We extract the audio from video.
File size: Up to 20 MiB and 10 minutes per file.
Jobs: Two active jobs per account on paid plans; one on the Free plan.
OpenAI SDKs: An OpenAI-compatible transcription endpoint: set the base URL to https://kalemio.app/v1 and the model to kalemio-arabic-1. It answers in the same request, waiting up to 100 seconds; a job still running then returns 504 transcription_pending with its job ID to resume.

File formats and limits Use it with the OpenAI SDKs

Your recordings stay yours.

Training: We don’t use your recordings to train models.
Audio: Working audio is deleted after processing.
Results: Yours to download for 24 hours after submission.

How we handle your data About the Arabic transcription API

Just need a subtitle file?

Arabic Subtitles is a separate no-code product for creating SRT files. These guides cover subtitle workflows; the Kalemio API remains the product for software integrations.

Generate an Arabic SRT without writing code

Arabic dialects.Every word, timed.