Keamanan & Privasi
Nyaéta naon anu lumangsung ka audio jeung transcripts anjeun dina unggal léngkah. No marketing fluff - ngan kumaha éta bener-bener gawé.
Tiga Tingkat Privasi
Standar
Saben pangguna, saben rencana — kalebu gratis
- HTTPS (TLS 1.3) kanggo kabeh data sing ditransfer
- Audio dipateni langsung sawise diproses
- Transkrip sing disimpan ing basis data kita
- Kita bisa maca transkripsi sing disimpan
- Data ora pernah dijual utawa digunakake kanggo latihan
- Hapus data kapan wae
Transkrip pribadi
Pro+ Available on Pro and Business plans
- Kabeh ing Standar, ditambah:
- Transkrip dienkripsi ing browser sampeyan (AES-256-GCM) sadurunge disimpan
- Kita mung nyimpen data sing dienkripsi — kita ora bisa maca
- Kunci dijupuk saka sandi sampeyan, ora pernah dikirim marang kita
- ⚠ Audio isih diproses ing pelayan kita nalika transkripsi
Cloud pribadi / Self-Hosted
Full isolasi — saka $99/mo
- Audio ora bakal ninggalake infrastrukturmu
- Transkripsi dijalanake ing GPU sampeyan
- Ora ana data sing dikirim menyang STT.ai pelayan
- Dukungan Air-gapped ana
- Kepribadian pungkasan-nganti-akhir
Apa sing kedadeyan karo data sampeyan
A transparan, léngkah-lengkah breakdown tina kumaha audio jeung transcript anjeun diurus.
Standar (kabeh pangguna)
1
Sampeyan ngetutake audio utawa rekaman langsung
Berkas anjeun bakal dikirim liwat HTTPS (TLS 1.3) ka pelayan GPU kami pikeun transkripsi.
2
Audio diproses ing memori
Model AI urang ngatranskripsikeun audio anjeun dina GPU. Audio disimpen dina memori nalika diolah — henteu pernah ditulis kana disk — sareng dihapus tina memori langsung saatosna.
3
Transkrip wis disimpan ing basis data kita
Transkrip teks, tanda waktu, jeung label panyatur disimpen supados anjeun bisa ngaksesna engké. Kami bisa maca data ieu (ku kituna pencarian, ringkasan AI, jeung babagi damel).
4
Sampeyan bisa mbusak kabeh kapan wae
Pamekar transkripsi individu atawa sakumna akun anjeun ti Pengaturan Privasi. Pamekaran permanen sareng langsung. Tetapan Privasi
With Private Transcript enabled
Langkah 1-2 padha — audiomu kudu diproses ing pelayan kita kanggo ngasilake transkripsi. Perbedaan iku apa sing kelakon sabanjuré:
3
Transkrip dienkripsi ing panyelesaian sadurunge disimpan
Sanggeus ditranskripsikeun, hasilna dipulangkeun ka peramban anjeun. Peramban anjeun bakal nyumputkeunana ku AES-256-GCM nganggo konci anu diturunkeun tina kecap akses anjeun (PBKDF2, 100K iterasi). Blob anu dienkripsi diutus ka pelayan kami pikeun disimpan. Kami henteu kantos ningali atanapi nyimpen konci enkripsi.
4
Kita mung nyimpen data sing dienkripsi
Pangkalan data urang ngan ngandung blob anu dienkripsi. Kami teu tiasa nyaring éta. Upami pangkalan data urang dirobek, transkripsi anjeun moal tiasa dibaca.
Penting: Transkripsi Pribadi ngajaga transkripsi anu disimpan. Saatos prosés transkripsi, audio anjeun diolah dina server kami pikeun ngahasilkeun teks. Upami model ancaman anjeun meryogikeun audio henteu kantos nyambung ka server pihak katilu, pikirkeun Awan Pribadi atanapi Self-Hosted. Awan Pribadhi
Apa sing bisa lan ora bisa dideleng
Kita ORA bisa ndeleng (kaliyan Transcript Pribadi)
- Teks transcript sing disimpan
- Nama utawa label pamicara (disimpen)
- Templat utawa data tingkat tembung (disimpen)
- Sandi utawa kunci penyulitanmu
Kita bisa ndeleng (utawa karo Private Transcript)
- Audio sampeyan nalika diproses (dihapus sawise)
- Nama berkas, ukuran, durasi (metadata)
- Basa ditemokake, model kang digunakake
- Timestamp of transcription
- Informasi akun lan mbayarmu
Rincian Teknis
| Algorithm enkripsi | AES-256-GCM (penyulitan sing diverifikasi) |
| Derivasi kunci | PBKDF2 karo SHA-256, 100.000 iterasi |
| IV (nonce) | 12 bayt acak saben enkripsi (ora pernah digunakake maneh) |
| Penyimpanan Kunci | Ora disimpen — dijupuk saka tembung sandhi saben sesi |
| Penyulitan transportasi | TLS 1.3 (HTTPS) + HSTS (1 taun, dimuat sadurunge) |
| Penyimpanan audio | Diproses ing memori, ora tau ditulis ing disk, dipateni langsung |
| Implementasi | Web Crypto API (browser-native, ora ana pustaka luar) |
| Kode sumber | github.com/sttaigit/stt-encryption (Lisensi MIT) |
Transkrip pribadi
Transkrip pribadi iku opt-in amarga enkripsi transkrip sing disimpan bakal mbatesi sawetara fitur:
Nggunakake enkripsi
- Nglakoni transkrip
- Eksport (TXT, SRT, VTT, lsp.)
- Ngundhuh
- Ngedit (di-enkripsi ing browser)
Ora ana karo enkripsi
- Pencarian ing sisih pamilik liwat transcript
- Ringkasan AI lan chatting (panyedhiya ora bisa maca data)
- Bagikan umum liwat tautan
- Kerjasama ruang kerja tim
Audio sing ora bakal ninggalake server sampeyan?
Transkrip pribadi nyegah transkrip nalika ora digunakaké, nanging audio tetep ngliwati GPU nalika diproses. Yen kabutuhan keamanan utawa kepatuhan sampeyan mbutuhake audio ora bisa nyambung karo infrastruktur pihak katelu, iki pilihan sampeyan:
Awan Pribadhi
$499/mnt
Pelayan GPU khusus anu diurus ku kami. Audio anjeun henteu pernah ninggalkeun lingkungan terisolasi Anda.
- Dedicated A100 GPU
- Diisolasi — ora ana infrastruktur dibagi
- Audio mung diproses ing piranti kerasmu
- Full API akses + SLA
Ditata dhewe
$99/mnt
Gambar Docker. Pelayanmu. GPUmu. Ora ana sing ninggalake jaringanmu.
- Docker — dabil edozein NVIDIA GPU
- Dukungan Air-gapped — ora perlu internet
- Model anyar kalebu
- Kontrol lengkap, privasi lengkap
Kewajiban kita (Semua Pengguna, Seluruh Rencana)
- File audio bakal dipateni ing 24 jam kanthi standar. Diolah dina memori GPU, sumber audio dipiceun sanggeus transkripsi. Sahiji-hijina pengecualian: lamun anjeun milih "Contribute corrections + audio to Voice Lab" dina Pengaturan Privasi, audio diarsipkeun nepi ka 90 poé sakumaha anu dipikabutuh ku cron pikeun ngahasilkeun segment anu dipotong dina CC-BY-SA-4.0. Tetapan Privasi
- Data sampeyan ora pernah digunakake kanggo latihan AI kajaba anjeun milih dina Privacy Setting (latihan panyesuaian teks-only sareng / atanapi kontribusi audio Voice Lab — kaduana dimatikan). Tetapan Privasi
- Kita ora adol datamu. Ora ana.
- Sekabeh lalu lintas dienkripsi nalika ditransfer liwat TLS 1.3 karo HSTS.
- Hapus data kapan wae saka Setelan Privasi utawa kanthi mbusak akun sampeyan. Tetapan Privasi
- Kode enkripsi iku sumber terbuka — audit iku dhewe (MIT lisensi). audit it yourself
Penyulitan sumber terbuka
pustaka enkripsi urang lengkep open-source di handapeun lisénsi MIT. Jangan percaya kami — verifikasi kode. Tidak perlu kepercayaan, hanya matematika.
Lihat ing GitHub | Lihat sumberSiap kanggo ngrekam kanthi aman?
Unggah file pertama gratis. Transkripsi pribadi kasedhiya ing rencana Pro lan Business.
Mulai PenulisanTakon-takon sing asring diajukake
STT.ai security and encryption runs in your browser: paste a URL, upload a file, or record from your mic. STT.ai picks the AI model and returns the transcript in under 5 minutes. Export as TXT, SRT, VTT, DOCX, JSON, or PDF.
Yes — every visitor gets 600 free minutes/month on STT.ai, usable for STT.ai security and encryption the same as any other workflow. Paid plans starting at $5/month unlock longer files, private transcripts, and priority queueing.
STT.ai security and encryption runs on the same AI models as the rest of STT.ai — our best models reach 95-97% accuracy on clean speech (3-5% Word Error Rate on benchmarks). Switch models on the fly if the first pass is below your target.
STT.ai security and encryption can run on any of STT.ai's 10+ models — STT.ai Enhanced (most accurate), Whisper Large V3 (99 languages), NVIDIA Canary (#1 WER on supported langs), Whisper Turbo (fast), Moonshine (lightweight), and more.
Yes. Every transcript exports as SRT or VTT — works with YouTube, Vimeo, TikTok, VLC, and every major video player. The burn-subtitles tool overlays them onto video as hardsubs.
Yes. Speaker diarization automatically labels each voice (Speaker 1, Speaker 2, ...) and you can rename them in the built-in editor. Works across all models and languages.
Most STT.ai security and encryption jobs finish in under 5 minutes. A 1-hour audio file typically completes in 2-3 minutes with our fastest models. Speed depends on chosen model and current GPU load.
STT.ai security and encryption accepts 20+ formats — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, and more. Output to TXT, SRT, VTT, DOCX, JSON, or PDF.
Yes. Audio files submitted to STT.ai security and encryption are processed and deleted by default. Pro plans add client-side encryption — even if STT.ai's database is breached, your transcripts are unreadable without your key. Data is never used for model training without explicit opt-in.
Yes. STT.ai offers a REST API with Python and Node.js SDKs, plus an MCP server for Claude and Cursor — all usable for STT.ai security and encryption workflows. Free API tier includes 100 minutes/month.
Yes. Every transcript opens in the built-in editor where you can correct words, rename speakers, adjust timestamps, and add notes. All changes save automatically.
Every transcript gets a unique shareable URL. Export to DOCX or PDF for email. Pro plans add password-protected and permanent links — useful for client work.
STT.ai handles 1,300+ platforms including YouTube, Vimeo, TikTok, SoundCloud, Zoom, Google Meet, podcast hosts, and more. URL transcription works with publicly-available content only — DRM-protected sources can't be transcribed.