Report Bug / Feature Request

Private Cloud Transcription

Your data never leaves your servers. Dedicated GPU transcription for organizations that demand complete control over their audio data.

Get Started Learn about our security

How It Works

Get up and running in three steps.

1. Deploy

We provision a dedicated GPU server in your preferred region or deploy our Docker image on your own hardware. Setup takes less than 24 hours.

2. Transcribe

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. Export

Transcripts stay on your server. Export as TXT, SRT, VTT, DOCX, JSON, or PDF. Integrate with your existing systems via API.

Choose Your Deployment

Feature Shared Cloud Private Cloud Self-Hosted License
Starting price $0 - $39/mo $499/mo $99/mo
Infrastructure Shared GPU Dedicated GPU Your own GPU
Data location Our servers Your chosen region Your premises
Air-gapped support
SLA
Fully managed You manage
Unlimited minutes

Built for Regulated Industries

When compliance requires that audio never leaves your infrastructure.

Healthcare

HIPAA-compliant transcription of patient recordings, clinical notes, and telehealth sessions.

Legal

Depositions, court recordings, and privileged communications stay within your firm.

Government

Classified or sensitive briefings transcribed on air-gapped networks. Full data sovereignty.

Finance

Earnings calls, compliance recordings, and trading floor audio processed on-premises.

Pricing

Private Cloud

$499/mo

Your own dedicated GPU server. Audio never leaves your infrastructure. True end-to-end privacy.

  • Dedicated A100 GPU
  • Isolated server — no shared infrastructure
  • Audio processed on your hardware only
  • Full API access + SLA
  • Unlimited minutes

Self-Hosted License

$99/mo

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

  • Docker image — runs on any NVIDIA GPU
  • Air-gapped support — no internet required
  • Model updates included
  • Full control over your data
  • Unlimited minutes

Ready to take control of your transcription infrastructure?

Tell us about your requirements. We'll help you choose the right deployment option.

Get Started

Frequently Asked Questions

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.
Thanks!
How was your experience?