Is this Mandarin speech-to-text really free?

Yes. The page is public, no signup is required, and there are no length limits. The recognition model runs entirely in your browser. For higher accuracy on noisy or accented audio, run your file through Subformer's cloud transcription in Subtitles-only mode.

How does the Mandarin transcription work in the browser?

It uses an open-source neural speech recognition model, executed by a WebAssembly runtime on your own device. The model (~75 MB) is downloaded on first use and cached in your browser. Subsequent visits skip the download entirely and can transcribe offline.

Is my audio uploaded to a server?

No. Recognition runs locally in your browser. The only network calls are to download the model and the WebAssembly runtime - both are static assets. Your audio file and the generated transcript never leave your device.

What audio formats are supported?

Anything your browser can decode: MP3, WAV, M4A, AAC, FLAC, OGG/Opus, plus video containers like MP4, MOV, and WEBM (the audio track is extracted automatically).

Can I download SRT or VTT subtitles?

Yes. After transcription you can download the result as plain text (.txt), SubRip subtitles (.srt), or WebVTT (.vtt) - both subtitle formats include segment-level timestamps so you can drop them straight into any video editor or player.

Tiny vs Base - which model should I pick?

Tiny (~40 MB) is fastest and great for clean studio audio. Base (~75 MB) is roughly twice as accurate on noisy or accented audio and only slightly slower. If you're not sure, start with Base - it's the default. For the highest accuracy on hard audio (accents, noise, overlap), use Subformer's cloud transcription in Subtitles-only mode.

Does it work offline?

Once the model is cached, yes. The first visit needs network access to download it; after that the page can transcribe audio offline.

Which browsers are supported?

Any modern browser with WebAssembly: Chrome, Firefox, Safari 15+, Edge, and Chromium-based mobile browsers.

Subformer

Mlebu

Gratis · Tanpa daftar · Mlaku ing browser sampeyan

Gratis Mandarin Ucapan menyang Teks

中文

Seret file audio utawa video Mandarin lan éntuk transkrip lengkap karo cap wektu - kabèh ing browser sampeyan, tanpa ndaftar. Model diundhuh sepisan (~75 MB) lan disimpen lokal, dadi mlaku sabanjure langsung lan bisa digunakaké offline.

Mriksa dukungan browser…

Butuh akurasi luwih dhuwur utawa luwih akeh basa?

Speech to Text Mandarin adhedhasar awan

Piranti gratis ing browser nglakokake model open-source cilik - apik kanggo audio sing resik, nanging bisa uga angel karo aksen Mandarin sing abot, swara, utawa pamicara sing tumpang tindih, lan mung nyakup sawetara basa sing winates. Kanggo akurasi kelas siaran, dhukungan basa sing luwih jembar, lan unduhan SRT/VTT/TXT, gunakake Speech to Text adhedhasar awan sing mbayar.

Coba Speech to Text adhedhasar awan

Carane kerjane

1. Seret file
Lebokaké sembarang audio utawa video Mandarin - MP3, WAV, M4A, MP4, lan WEBM kabèh didhukung.
2. Transkripsikake
Klik pisanan bakal ngundhuh model ~75 MB menyang browser sampeyan. Sawisé kuwi, pengenalan langsung lan bisa digunakaké offline.
3. Unduh
Simpen transkrip minangka TXT, SRT, utawa VTT. Audio lan asil sampeyan ora bakal tau ninggalake piranti.

Audio sampeyan tetep ana ing piranti sampeyan

Pengenalan mlaku kabeh ing browser sampeyan nggunakake WebAssembly. Siji-sijiné panyuwunan jaringan yaiku kanggo njupuk model lan runtime WebAssembly - loro-loroné minangka aset publik sing statis. Kita ora ndeleng audio sampeyan lan kita ora ndeleng transkrip.

Carane transkripsi Mandarin mlaku ing browser sampeyan

Pangenalan swara biasane tegese ngunggah audio sampeyan menyang GPU wong liya. Ing kene model mlaku ing mesin sampeyan dhewe, sing ndadekake iki gratis lan pribadi ing wektu sing padha.

Open-source recognition model: Model neural open-source sing dilatih ing audio multibasa - mulane siji unduhan nangani Mandarin tanpa model khusus basa sing kudu dijupuk.
WebAssembly: Runtime inferensi dikompilasi menyang WebAssembly, saengga kode numerik mlaku kanthi kacepetan meh asli ing tab sing di-sandbox tanpa plugin lan tanpa instalasi.
On-device inference: Model kuantisasi ~75 MB dimuat lan loop dekoding didorong kabeh ing sisih klien. Ora ana ing pipeline sing nelpon server sawise kaca wis dimuat.
Web Audio API: File sampeyan didekode lan disampel ulang menyang mono 16 kHz sing dikarepake model nggunakake pipa audio browser dhewe, saengga format apa wae sing bisa diputer browser sampeyan ditampa.

Premium - uga saka Subformer

Terjemah & sulih swara

Terjemahake lan sulih swara video menyang 30+ basa kanthi siji klik.

Terjemahake subtitle

Lebokaké SRT utawa VTT lan éntuk terjemahan rapi ing sembarang basa.

Editor subtitle

Asah, atur wektu, lan ganti gaya subtitle sampeyan ing editor gratis ing browser.

Gratis Mandarin Ucapan menyang Teks

Speech to Text Mandarin adhedhasar awan

Carane kerjane

1. Seret file

2. Transkripsikake

3. Unduh

Audio sampeyan tetep ana ing piranti sampeyan

Carane transkripsi Mandarin mlaku ing browser sampeyan

Pitakon sing asring ditakoni

Coba basa speech-to-text gratis liyane