Speech to text · الشامي

Levantine Arabic audio to text, free

Upload a voice note, a call recording or a video and get Levantine 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. Shami grammar stays in the transcript (بدي, رح, ولا), though a few dialect spellings come back in their standard form.

MP3, M4A, WAV, WhatsApp .opus, MP4 · up to 2 min free

Upload a voice note, call recording or video in Levantine Arabic, or record yourself. Free up to 2 minutes a file, 3 files a day, no account.

Valmiki STT

Your transcript appears here, exactly as Valmiki returns it.

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.

Levantine Arabic audio to text converter

Drop in an audio or video file and get Levantine 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 Levantine Arabic, including English words in the middle of a sentence.

Free Levantine Arabic speech to text: what you get

Files up to 2 minutes, 3 a day on each device, with no account.
With a free account, files up to 10 minutes and 10 MB each in the dashboard or the API, billed by the second.
The transcript in Levantine Arabic, in Roman (English) letters, and translated into English.
Copy the text or download plain text (TXT) or Word (DOCX), and subtitles (SRT) for uploaded files.

Levantine Arabic voice to text, saved as text, Word or subtitles

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.

Real transcripts

What Valmiki STT returned for Levantine Arabic.

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.

Clean recordingReal output, 25 October 2026

What was said: مرحبا، بدي أعرف إذا الطلبية رح توصل اليوم ولا بكرا، لأنه ما رح كون بالبيت بعد الضهر.; Hi, I'd like to know whether the order will arrive today or tomorrow, because I won't be home in the afternoon.
What Valmiki STT returned, unedited: مرحبا، بدي اعرف إذا الطلبية رح توصل اليوم ولا بكرا، لأنه ما رح كون بالبيت بعد الظهر.

One of two clean runs. The other wrote بكرة for بكرا and added a letter, أكون for the spoken كون.

Phone quality (8 kHz)Real output, 25 October 2026

What was said: مرحبا، بدي أعرف إذا الطلبية رح توصل اليوم ولا بكرا، لأنه ما رح كون بالبيت بعد الضهر.; Hi, I'd like to know whether the order will arrive today or tomorrow, because I won't be home in the afternoon.
What Valmiki STT returned, unedited: مرحبا، بدي اعرف إذا الطلبية رح توصل اليوم ولا بكرة، لأنه ما رح كون بالبيت بعد الظهر.

Same transcript in both phone-quality runs.

How to judge the accuracy yourself

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 Levantine 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 Levantine Arabic

How Levantine Arabic speech comes out as text.

Levantine Arabic, Shami, is spoken in Syria, Lebanon, Jordan and Palestine. Its future marker رح (will), بدي (I want) and ولا (or) do not exist in Fusha. On our test sentence Valmiki STT kept all of them in every run, along with the spoken كون (be) in three runs of four.

Spelling moved towards the standard in places. الضهر (afternoon), as Levantine speakers say and often type it, came back as the standard الظهر in all four runs, and بكرا (tomorrow) came back as بكرة in three. The hamza on أعرف was usually dropped. The meaning was right every time.

Transcript script: Arabic script. Dialect grammar is kept; some words come back in their standard spelling (الظهر for الضهر).
Language setting: None. Valmiki STT detects the spoken language, including switches mid-sentence.
Price after the free files: $0.00525 per minute of audio, billed by the second.
In local currency: About JOD 0.0037 a minute (JOD 0.2233 an hour of audio), at exchange rates from open.er-api.com, 25 October 2026.
Files: MP3, M4A, WAV, AAC, FLAC, AMR, WhatsApp .opus and .ogg, and MP4 or MOV video in the uploader. The API takes WAV, MP3, FLAC, OGG, Opus, WebM, AAC and M4A files up to 10 MB and 10 minutes.

Dialects and mixing

Syrian, Lebanese, Jordanian and Palestinian speech.

Levantine speakers understand each other easily, but the accents differ: city speech in Damascus and Beirut turns ق into a glottal stop, while Jordanian and rural Palestinian speech often says it as g, and the final ـة is said as -e in much of Lebanon and Syria. Our test voice spoke a general Levantine. We have not tested the regional differences, so try your own callers' recordings.

Lebanese speech mixes in French (ميرسي, bonjour, ça va) and Jordanian and Gulf-based Levantine speech mixes in English. Valmiki STT detects language switches without a setting, but we have not tested French inside Levantine Arabic; test it if your audio has a lot of it.

Use cases

What people turn into Levantine Arabic text.

WhatsApp voice notes to Levantine Arabic text

Voice notes from family in Damascus or Amman, from a landlord in Beirut, or from a customer. Upload the .opus file and read the Shami, or switch to English to pass it on.

YouTube videos to Levantine Arabic text

Levantine podcasts, cooking channels, comedy and interviews. For your own channel, download the MP4 from YouTube Studio and use the SRT file as a start on captions.

Interviews and meetings

Interviews for journalism and NGO research in Jordan and Lebanon, where people answer in dialect. Upload parts of up to 10 minutes after a free sign-up and download a Word file.

Call recordings

Delivery, banking and clinic calls in Amman and Beirut, and Gulf contact centres serving Levantine customers. Read what was agreed instead of replaying the call.

Voice typing

How to voice-type in Levantine Arabic.

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 Jordan, Lebanon, Palestine or Syria if listed, 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 Levantine Arabic is not offered there, save the voice note and upload it above.
4. Microsoft Word
Word's Dictate lists Arabic only for Bahrain, Egypt and Saudi Arabia, as preview languages (checked October 2026). Google Docs voice typing has Arabic (Jordan), (Lebanon) and (Palestine); dictate there and download a Word file.
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.

For recordings longer than a minute, use the uploader above.

API

Levantine Arabic speech to text API.

Send a recording to POST /v1/transcribe and read the Levantine Arabic text from the reply. There is no language parameter. $0.00525 per minute of audio, billed by the second.

transcribe.py

1# pip install requests
2import requests
3
4with open("shami-voice-note.ogg", "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"])              # مرحبا، بدي اعرف إذا الطلبية رح توصل ...
16print(result["duration_seconds"], "seconds of audio")

About JOD 0.0037 a minute (JOD 0.2233 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

Levantine Arabic speech to text, answered.

Yes, for short files. The uploader on this page turns Levantine 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 Levantine 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 Levantine 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 Levantine 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 Levantine Arabic text, because a word misheard in Levantine Arabic carries into the English.

Yes, in the uploader's Roman script tab, which writes the transcript in Latin letters. It is not guaranteed to match the Arabizi people type in chats, so check it. The API returns Arabic script.

On our test sentence, good: every run kept the Levantine grammar and the meaning, with الضهر normalised to الظهر and بكرا often to بكرة. That is one sentence, not a benchmark; test recordings from your own city.

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.

It kept them on our test: بدي, رح, ولا and كون came back as spoken. A few spellings were standardised, such as الضهر written الظهر.

Other languages, and the other direction.

Need the reverse? Turn Levantine Arabic text into speech with Pāṇini TTS, free to try without an account.

See speech to text in every language we have tested.

Turn your Levantine Arabic audio into text.

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.

Upload a file Valmiki STT API