Speech to text · العربية
Upload a voice note, a call recording or a video and get Arabic text back. It is free for files up to 2 minutes without an account (3 files a day); longer files need a free account. Download the result as text, Word or subtitles. The transcript is in Arabic script, for Modern Standard Arabic and for the spoken dialects alike, with no dialect to choose.
Upload a voice note, call recording or video in Arabic, or record yourself. Free up to 2 minutes a file, 3 files a day, no account.
Upload MP3, M4A, WAV, AAC, FLAC, AMR, a WhatsApp voice note (.opus or .ogg) or an MP4 or MOV video, or record up to 2 minutes from your microphone. Switch between Arabic script, Roman script and an English translation (made by Vyas, our language model, when you open the tab), then copy the text or download TXT or DOCX, plus SRT subtitles for uploaded files. No account needed for files up to 2 minutes, 3 a day.
Drop in an audio or video file and get Arabic text back in Arabic script. It reads MP3, M4A, WAV, AAC, FLAC and AMR audio, WhatsApp voice notes (.opus and .ogg) and MP4 or MOV video, and the file is decoded on our server, so it works the same on an iPhone. You can also record from your microphone. There is no language menu: Valmiki STT, the speech recognition model behind it, works out that the speech is Arabic, including English words in the middle of a sentence.
Copy the transcript, or download it as a TXT file or a Word document. For an uploaded file you also get an SRT subtitle file to load into YouTube Studio or a video editor. Long recordings after sign-up cost $0.00525 per minute of audio, billed by the second, the same for every language.
ارفعوا رسالة صوتية من واتساب أو تسجيل مكالمة أو مقطع فيديو، واحصلوا على النص بالعربية. الخدمة مجانية للملفات حتى دقيقتين دون إنشاء حساب، بحد ثلاثة ملفات في اليوم، وللملفات الأطول يكفي حساب مجاني.
لا حاجة لاختيار اللغة أو اللهجة: يتعرّف Valmiki STT على العربية تلقائيًا، فصحى كانت أو عامية، مع الكلمات الإنجليزية داخل الجملة. ويمكن تنزيل النص بصيغة TXT أو Word أو ملف ترجمة SRT، مع ترجمة إلى الإنجليزية.
النصوص المعروضة في هذه الصفحة هي ما أرجعه النظام فعلًا، دون أي تعديل. جرّبوا تسجيلًا يشبه تسجيلاتكم قبل الاعتماد على الخدمة.
Real transcripts
Each sentence was read by Nour, a Pāṇini TTS voice, and sent to Valmiki STT as a file: twice as the clean recording and twice as an 8 kHz phone-quality copy (squeezed down to 8 kHz and back, the way a phone line does it). The transcripts are shown exactly as they came back, errors included. Tested 25 October 2026. These are synthetic clips, not recorded calls.
Same transcript in both clean runs. Every word is right; the shadda on مرّ was dropped and مرحبًا was written مرحباً, a spelling variant.
One of two phone-quality runs, without the tanween on مرحبا. The other matched the clean transcript.
No public benchmark includes Valmiki STT, so we do not publish a table comparing it with other services. Judge it on audio like yours instead. Play each clip above and compare what was said with what came back, word by word. Then upload a recording of your own that is close to what you will really transcribe: the same kind of phone line or microphone, the same speakers, the same mix of Arabic and English. Count the words that changed meaning, not the spelling variants, and try the 8 kHz case if your audio comes from calls.
About Arabic
Modern Standard Arabic (الفصحى) is the Arabic of news bulletins, lectures, khutbas, official statements and most audiobooks, and it is the easiest case for a transcriber because it is also the written standard. On our test sentence Valmiki STT returned every word right in all four runs, clean and 8 kHz.
What changed was spelling detail. The shadda (ّ) on مرّ was dropped every time, and the tanween on مرحبًا moved onto the alif (مرحباً) or disappeared (مرحبا). Short vowels are not added. Both habits match how most Arabic is typed, but if you need fully vocalised text, add the diacritics afterwards.
Dialects and mixing
Most audio people want to turn into text is not Fusha: voice notes and calls are in Egyptian, Gulf, Levantine, Iraqi or Maghrebi Arabic. Valmiki STT has one Arabic language and no dialect setting. We tested five dialects as well, each with its own page and real transcripts: the dialect words stayed dialect (لسه, أبي, بدي, هسه, وش), while some spellings were pulled towards the standard, such as الضهر written الظهر and the Iraqi أكدر written أقدر.
We have not tested Moroccan, Algerian, Tunisian or Sudanese Arabic. Darija in particular is far from Fusha and full of French, so test your own recordings before relying on it. Gulf Arabic with English words in Latin letters is covered on the Gulf Arabic page; it is the hardest case we have tried.
Use cases
Voice notes from colleagues, a landlord or a supplier, in Fusha or in dialect. Upload the .opus file and read the Arabic, or open the English tab to forward it to someone who does not read Arabic.
Lectures, khutbas, news reports and documentaries in Fusha. For videos on your own channel, download the MP4 from YouTube Studio and use the SRT file as a start on Arabic captions.
Interviews for research and journalism, conference talks and recorded meetings. Upload parts of up to 10 minutes after a free sign-up and download a Word file to quote from.
Recorded customer calls for teams across the region. Read or search the text for what was asked and promised; at volume, send the recordings to the API.
Voice typing
Voice typing is a different job from transcribing a file: you speak and the words appear as you go. Sonex Labs has no voice-typing keyboard or app, so for that, use the tools already on your phone or computer.
1. Android phone (Gboard)
Install Gboard, add Arabic under Languages in its settings and pick your country's variant, then tap the microphone on the keyboard.
2. iPhone
Add the Arabic keyboard in Settings, then General, Keyboard, Keyboards. If your iPhone offers dictation for Arabic, a microphone key appears on that keyboard.
3. WhatsApp
To type a message by voice, tap the microphone on your keyboard, not the voice-note button in WhatsApp; the keyboard writes the words into the chat box. WhatsApp can also show a transcript under a received voice message in some languages (Settings, then Chats, then Voice message transcripts). If Arabic is not offered there, save the voice note and upload it above.
4. Microsoft Word
Word's Dictate lists Arabic (Bahrain), Arabic (Egypt) and Arabic (Saudi Arabia) as preview languages, which Microsoft says may be less accurate and add less punctuation.
5. Windows
Windows 11 voice typing does not list Arabic (checked October 2026). On a PC, use Google Docs voice typing in Chrome or Edge, which offers Arabic and 14 country variants.
For recordings longer than a minute, use the uploader above.
API
Send a recording to POST /v1/transcribe and read the Arabic text from the reply. There is no language parameter. $0.00525 per minute of audio, billed by the second.
1# pip install requests2import requests34with open("arabic-call.wav", "rb") as audio:5 r = requests.post(6 "https://api.sonexlabs.com/v1/transcribe",7 headers={8 "Authorization": "Bearer YOUR_API_KEY",9 "Content-Type": "audio/wav", # audio/mpeg, audio/ogg (WhatsApp notes), audio/mp4 ...10 },11 data=audio,12 )13r.raise_for_status()14result = r.json()15print(result["text"]) # مرحباً، طلبي لم يصل حتى الآن ...16print(result["duration_seconds"], "seconds of audio")About SAR 0.020 a minute (SAR 1.181 an hour of audio); AED 0.019 a minute (AED 1.157 an hour of audio); EGP 0.29 a minute (EGP 17.41 an hour of audio), at exchange rates from open.er-api.com, 25 October 2026. Live streaming, limits and error codes are on the speech to text API page, and plans are on pricing.
FAQ
Yes, for short files. The uploader on this page turns Arabic audio into text with no account for files up to 2 minutes, 3 files a day. For longer files, sign up free and transcribe files of up to 10 minutes and 10 MB each in the dashboard or through the API; that costs $0.00525 a minute, billed by the second, so a 10-minute recording costs about 5.25 US cents.
There is no app to install. The uploader works in the browser on a phone too: open this page on Android or iPhone, pick a voice note, recording or video from your files, and read the Arabic text. For typing by voice as you speak, use your phone keyboard's microphone, as described in the voice-typing steps above.
Yes. It runs in a current browser: Chrome, Edge, Firefox or Safari on a Windows PC or a Mac, and Safari or Chrome on an iPhone or Android phone. Files are decoded on our server, so an iPhone voice memo, a WhatsApp .opus note or a MOV video works the same as on a PC. There is nothing to install.
Long-press the voice note in WhatsApp and share or export it to your files; on Android, received voice notes are also kept as .opus files in WhatsApp's media folder. Upload the .opus or .ogg file here and the Arabic text appears. Notes up to 2 minutes need no account.
Upload the audio, then open the English tab above the transcript. Vyas, our language model, translates the Arabic transcript when you open the tab, and you can copy it or download it like the transcript. Check names, amounts and dates against the Arabic text, because a word misheard in Arabic carries into the English.
Yes, in the uploader's Roman script tab, which writes the transcript in Latin letters. The API returns Arabic script. If you want the Arabizi people type in chats, with 3 for ع and 7 for ح, check the Roman text before you use it.
For Fusha, very good on our test: every word right in all four runs, with diacritics simplified. Dialects keep their own words but some spellings shift towards the standard; each dialect page shows its own runs. That is one sentence per variety, not a benchmark, so test recordings like yours.
Without an account, 2 minutes per file and 3 files a day. With a free account, up to 10 minutes and 10 MB per audio file in the dashboard or the API, billed by the second. For anything longer, split the recording into parts of 10 minutes or less and send each one; the API takes the same limit.
No, and you do not need to. Valmiki STT takes Arabic as one language and detects it for you. In our tests the dialect words came back as dialect, not translated into Fusha.
Related
Need the reverse? Turn Arabic text into speech with Pāṇini TTS, free to try without an account.
Answering Arabic phone calls rather than transcribing them? See Arabic voice agents.
Free for files up to 2 minutes without an account. Longer files, with a free account: $0.00525 per minute of audio, billed by the second.