Informa d' errors / Petició de característiques

Transcripció privada de Cloud

Les vostres dades mai deixen els vostres servidors. La transcripció de la GPU Didicada per a organitzacions que exigeixen el control complet sobre les seves dades d' àudio.

Get Started Apreneu de la nostra seguretat

Com funciona

Aixeca't i corre en tres passos.

1, Deploy

Hem provisional un servidor de GPU dedicat a la vostra regió preferida o despleguem la nostra imatge d' amarer en el vostre propi maquinari. La configuració tarda menys de 24 hores.

2, Trancric

Use the same STT.ai API and web interface you know. Audio is processed entirely on your dedicated server. Nothing is sent to shared infrastructure.

3. Exporta

Els Transcripts es queden al vostre servidor. Exporta com TXT, SRT, VT, DOCX, JSON, o PDF. Integrar amb els vostres sistemes existents mitjançant l' API.

Escolliu la vostra desplegament

Característica Núvol compartitweather condition Núvol privatweather condition Llicència auto-Host
S' està iniciant el preu $0 - $39/mounit description in lists $499/mounit description in lists $99/mounit description in lists
Infraestructura GPU compartida GPU Didicada La vostra pròpia GPU
Ubicació de dades Els nostres servidors La vostra regió seleccionada El vostre local
Funcionament amb l' aire
SLA
Totalment gestionat T'ho pots arreglar.
minuts sense límit

Es construeix per a l' Indústries Regulada

Quan el compliment requereix que l'àudio no deixi mai la vostra infraestructura.

SanitatcareCity name (optional, probably does not need a translation)

Recripcions que compleixen les gravacions de pacient, notes clínics i sessions telepolítiques.

Legal

Deposicions, gravacions judicials i comunicacions privilegiades segueixen dins la seva empresa.

Govern

Les reunions classificades o sensibles transcrivendes a les xarxes amb aire condicionat. Sobiranitat completa de dades.

Finances

Les trucades de les orelles, les gravacions de compliment, i l'àudio de terra comercial processada en rèpliques.

PricingCity name (optional, probably does not need a translation)

Núvol privatweather condition

$499/mounit description in lists

El vostre propi servidor GPU dedicat. L' àudio mai deixa la vostra infraestructura. La privacitat real a final.

  • A100 GPU Dedicat
  • El servidor isolat no disposa d' infraestructura compartida
  • S' ha processat l' àudio només en el maquinari
  • Accés complet de l' API + SLA
  • minuts sense límit

Llicència auto-Host

$99/mounit description in lists

Run STT.ai on your own hardware. Docker image, your servers, your rules.

  • L' argument d' imatge de Docker s' executa a qualsevol GPU NVIDIA
  • Funcionament amb l' aire condicionat no es requereix internet
  • S' han inclòs les actualitzacions del modelThe role of the transaction, in past tense
  • Control complet sobre les vostres dades
  • minuts sense límit

A punt per prendre el control de la teva infraestructura de la transcripció?

Parla'ns dels teus requisits, t'ajudarem a triar l'opció de desplegament correcta.

Get Started

Preguntes més freqüents

STT.ai Private Cloud and Self-Hosted transcription 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 Private Cloud and Self-Hosted transcription the same as any other workflow. Paid plans starting at $5/month unlock longer files, private transcripts, and priority queueing.

STT.ai Private Cloud and Self-Hosted transcription 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 Private Cloud and Self-Hosted transcription 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 Private Cloud and Self-Hosted transcription 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 Private Cloud and Self-Hosted transcription 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 Private Cloud and Self-Hosted transcription 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 Private Cloud and Self-Hosted transcription 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.
Gràcies!
Com va ser la teva experiència?