Speech to text · বাংলা
Upload a voice note, a call recording or a video and get Bangla 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 words came out right in our test, but the script varied: Bengali script in one run, Bangla in English letters in three. Check it on your own audio.
Upload a voice note, call recording or video in Bengali, 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 Bangla 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 Bangla text back in Bangla 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 Bangla, 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.
Real transcripts
Each clip was rendered by Pāṇini TTS and streamed to Valmiki STT twice: as a clean recording and as an 8 kHz phone-quality copy. The transcripts are shown exactly as they came back, errors included. Tested 24 October 2026. These are synthetic clips, not recorded calls.
One of two clean runs, word for word. The other came back in Latin letters.
Both phone-quality runs came back in Latin letters, with the words right.
No public benchmark includes Valmiki STT, so we do not publish a table comparing it with other services.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 Bangla 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 Bengali
Valmiki STT got the words right on our test clip, including the colloquial নাগাদ (by, around) and পার্সেলটা (the parcel). One clean run came back in Bengali script word for word; the other heard এখনো (still) as এখন (now).
The script is the catch. Three of four runs, including both 8 kHz phone-quality runs, came back as Bangla in Latin letters (amar parcel ta ekhono asheni) rather than Bengali script. There is no setting to force Bengali script yet, so test with your own recordings if your system needs it.
Dialects and mixing
Standard colloquial Bangla is shared by Kolkata and Dhaka with small differences: Dhaka speech says করসি where Kolkata says করছি, and each side has its own words for everyday things (পানি and জল for water). Our test sentence is neutral standard Bangla. Valmiki STT has one Bengali language, not a Bangladesh and an India version, so try a recording from your own side of the border.
Sylheti and Chittagonian (চাটগাঁইয়া) are a different matter. Many linguists treat them as separate languages, and a Kolkata listener often cannot follow them. Valmiki STT does not list either, and we have not tested them. Expect standard-Bangla spelling of what it hears at best, and test it before you rely on it for the Sylheti community in the UK or Chittagong callers.
Use cases
Bangla voice notes from family abroad, from a customer, or from a supplier in Dhaka or Kolkata. Upload the .opus file and read the Bangla, or open the English tab to share it with someone who does not read it.
Bangla news, cooking and education channels, and recorded waz and talks. For your own channel, download the MP4 from YouTube Studio and use the SRT file as a start on Bangla captions.
Interviews for journalism and research in West Bengal and Bangladesh, and recorded meetings. Upload parts of up to 10 minutes after a free sign-up and download a Word file.
E-commerce and courier calls about parcels, the most common Bangla support call. Read what each caller said instead of listening again, or send the recordings to the API in bulk.
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 Bangla (বাংলা) under Languages in its settings, choosing India or Bangladesh, then tap the microphone on the keyboard.
2. iPhone
Add the Bangla keyboard in Settings, then General, Keyboard, Keyboards. If your iPhone offers dictation for Bangla, 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 Bangla is not offered there, save the voice note and upload it above.
4. Microsoft Word
Word's Dictate does not list Bangla (checked October 2026). Voice-type in Google Docs instead (Tools, then Voice typing, then Bengali (India) or Bengali (Bangladesh)) and download the document as a Word file.
5. Windows
Windows 11 voice typing does not list Bangla (checked October 2026). Google Docs voice typing in Chrome or Edge does, so use that on a PC.
For recordings longer than a minute, use the uploader above.
API
Send a recording to POST /v1/transcribe and read the Bangla 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("bangla-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"]) # হ্যালো, আমার পার্সেলটা এখনো আসেনি। ... (or Bangla in Latin letters; see above)16print(result["duration_seconds"], "seconds of audio")About ₹0.50 a minute (₹29.93 an hour of audio); ৳0.65 a minute (৳38.97 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 Bangla 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 Bangla 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 Bangla 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 Bangla transcript when you open the tab, and you can copy it or download it like the transcript. Check names, amounts and dates against the Bangla text, because a word misheard in Bangla carries into the English.
Yes, in the uploader's Roman script tab, and sometimes without asking: three of four runs of our test clip came back as Bangla in English letters (amar parcel ta ekhono asheni). If you need Bengali script every time, use the Bangla tab and check it, because there is no setting to force it.
On our test clip the words were right in every run, with one slip (এখনো heard as এখন). The script was the problem: three runs of four were in Latin letters. That is one sentence, not a benchmark; try recordings like yours, from your region, before you depend on it.
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.
Yes. Bangla is the language's own name and Bengali the English one. This page covers Bangla as spoken in both West Bengal and Bangladesh.
Related
Need the reverse? Turn Bangla text into speech with Pāṇini TTS, free to try without an account.
Answering Bangla phone calls rather than transcribing them? See Bangla 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.