Skip to main content
Whisper Web
99 languages

Free Multi-Language Transcription — 99 languages

Transcribe audio in 99 languages with automatic language detection. From Mandarin to Swahili, Arabic to Portuguese — start from the audio to text converter for any supported recording. Free in your browser with OpenAI Whisper and no install. Free files stay on your device; Unlimited adds optional cloud upload.

Loading audio engine…

Built for a Multilingual World

99 languages Supported

Transcribe in English, Spanish, Mandarin, Arabic, Hindi, Portuguese, French, German, Japanese, Korean, Russian, Turkish, Vietnamese, Thai, Indonesian, and 90+ more languages.

Automatic Language Detection

Don't know the language? No problem. Whisper automatically detects the spoken language and transcribes accordingly. Works reliably even for less common languages.

Privacy Across Borders

free files stay on your device — critical for international organizations handling sensitive content across jurisdictions with different data protection laws (GDPR, LGPD, PIPA).

Multilingual Meeting Support

Transcribe meetings where participants speak different languages. Process each language segment separately for clean, accurate transcripts that capture every voice in the room.

Unicode-Ready Export

Full Unicode support in all export formats. TXT, SRT, VTT, and JSON outputs correctly handle CJK characters, Arabic script, Devanagari, Cyrillic, and every writing system Whisper supports.

Same Speed, Any Language

Processing speed is consistent across all languages. A 30-minute recording takes the same time to transcribe whether it's in English, Mandarin, or Swahili.

How to Transcribe in Any Language

1

Open Whisper Web

No account needed. No language packs to install. All 99 languages are built into the Whisper model. Just open whisperweb.dev.

2

Upload Your Audio

Drag and drop your audio file in any language. The AI will automatically detect the language, or you can specify it manually for better accuracy.

3

Get Your Transcript

The AI processes your audio locally with full Unicode support. Characters from any writing system render correctly in the transcript.

4

Export in Any Format

Export as TXT, SRT, VTT, or JSON. All formats properly encode non-Latin scripts, CJK characters, and right-to-left languages.

Perfect For

Transcribing multilingual meetings for international teams
Converting foreign-language interview recordings into text
Creating subtitles for videos in non-English languages
Transcribing international conference presentations and panels
Documenting interpreter-assisted conversations and negotiations
Processing multilingual customer support call recordings
Generating transcripts for language learning and translation work

Frequently Asked Questions

Is Whisper Web really free? Do I need an account?
In free local mode, audio is processed in your browser and is not uploaded. No account is required. Each file can be up to 20 minutes and 200 MB. There is no daily file-count limit. For longer files, Whisper Web Unlimited offers optional cloud processing with a per-file limit of 10 hours and 5 GB.
What is the official Whisper Web site?
The official Whisper Web site is https://whisperweb.dev. Other domains may use a similar name. Free local mode on whisperweb.dev runs in your browser without an account; each file is limited to 20 minutes and 200 MB.
Does my audio leave my device?
In free local mode, audio is processed in your browser and is not uploaded. Model files still download over the network the first time you use a model. Whisper Web Unlimited is an optional cloud workflow for larger files (up to 10 hours and 5 GB per file).
What if a result says Whisper Web but the address is different?
If a result says “Whisper Web” but the address is not whisperweb.dev, it is not the official Whisper Web site. Open https://whisperweb.dev to use free local transcription in your browser (20 minutes / 200 MB per file, no account).
Which languages does Whisper support?
Whisper supports 99 languages including: English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Chinese (Mandarin), Japanese, Korean, Arabic, Hindi, Bengali, Turkish, Vietnamese, Thai, Indonesian, Malay, Swahili, Polish, Czech, Swedish, Danish, Finnish, Norwegian, Greek, Hebrew, Romanian, Ukrainian, and many more.
How accurate is transcription for non-English languages?
Accuracy varies by language. High-resource languages (Spanish, French, German, Mandarin, Japanese) achieve accuracy close to English. Less-resourced languages may have lower accuracy, especially with accented speech or domain-specific vocabulary. Test with a short sample first to gauge quality for your specific language.
Can it transcribe audio where speakers switch between languages?
Whisper can handle code-switching to some degree, but accuracy is best when the audio is predominantly in one language. For meetings where participants speak different languages, we recommend noting timestamps and processing each language segment separately for the best results.
Does it handle tonal languages like Mandarin and Vietnamese?
Yes. Whisper was trained on diverse audio including tonal languages and produces accurate transcripts in Mandarin, Cantonese, Vietnamese, Thai, and other tonal languages. The output uses the standard writing system for each language (simplified/traditional Chinese characters, Vietnamese with diacritics, etc.).
Can I transcribe right-to-left languages like Arabic and Hebrew?
Yes. Whisper fully supports Arabic, Hebrew, Persian (Farsi), and Urdu. The transcript text is generated in the correct script, and exports properly encode RTL text. Your text editor or subtitle player handles the display direction.
Is language detection automatic?
Yes. By default, Whisper automatically detects the spoken language in the first 30 seconds of audio. For best accuracy — especially with short clips or uncommon languages — you can manually select the language before transcription. Auto-detection works reliably for the most commonly spoken languages.

Related Tools

Audio to TextConvert any audio file to text — MP3, WAV, M4A, FLAC and more.Audio TranslatorTranscribe and translate audio from 99 languages to English.Whisper TranscriptionUse OpenAI Whisper directly in your browser — no API key needed.AI TranscriptionAI transcription with editable, timestamped output.Speech to TextSpeech recognition powered by OpenAI Whisper, in your browser.

Continue with Unlimited-plan cloud transcription

Open the dashboard for Unlimited-plan cloud transcription, saved history, and batch workflows. Files selected there are uploaded for cloud processing.

Open the dashboard