Ka Papa Hana

Ka hoʻololiʻana i ka Cloud Private

ʻAʻole e haʻalele kāu ʻike i kāu mau mea lawelawe. Ka hoʻololi ʻana i ka GPU no nā hui e koi ana i ka hoʻokele piha ma luna o kā lākou ʻike leo.

Get Started E aʻo e pili ana i kā mākou palekana

Pehea e hana ai

E hoʻomaka a hoʻokō i ʻekolu mau ala.

Hoʻouka

Hoʻonohonoho mākou i kahi kikowaena GPU i hoʻolaʻa ʻia i kāu wahi makemake ʻia a i ʻole e hoʻohana i kā mākou kiʻi Docker ma kāu pono ponoʻī. ʻAʻole lōʻihi ka hoʻonohonoho ma mua o nā hola 24.

Hoʻouna

Hoʻohana i ka STT.ai API a me ka pūnaewele pūnaewele e ʻike ai ʻoe. Hoʻokō ʻia ka leo i kāu mea lawelawe i hoʻolaʻa ʻia. ʻAʻole e hoʻouna ʻia nā mea i ka hoʻokumu hoʻokaʻawale.

Kahu

E noho nā transcripts ma kāu mea lawelawe. Hoʻouna i ka TXT, SRT, VTT, DOCX, JSON, a i ʻole PDF. Hoʻohui me kāu mau hoʻonohonoho i kēia manawa ma o API.

Kahi

Hōʻike Hoʻokaʻawale i ka māla Kīwī kīwī Ka Mana Hoʻokipa
Ka kumukūʻai hoʻomaka $0 - $39/no $499/no $99/no
Hoʻokumu GPU hoʻokaʻawale GPU hoʻolaʻa Ko oukou pono GPU
Kahua Data Kākoʻo Ko oukou wahi i kohoia Ko oukou mau hale
Hoʻokō Air-gapped
SLA
Manaʻo piha E hoʻokele ʻoe
Nā minuke kāhea

Hoʻokumu no nā ʻoihana hoʻonohonoho

Inā pono ka hoʻokōʻana i ka leo eʻaʻole e haʻalele i kāu hana hana.

Ka mālama olakino

HIPAA-compliant transcription o nā kiʻi o nā maʻi, nā palapala lapaʻau, a me nā hālāwai telehealth.

Kānāwai

Hoʻokomoʻia nā waihona, nā hoʻopaʻa inoa o ka'aha'ōlelo, a me nā kamaʻilio hoʻomalu i loko o kāuʻoihana.

Ka Mana

Hoʻokaʻawale ʻia nā hōʻike ʻike a i ʻole nā ​​mea hoʻohālike i hoʻololi ʻia ma nā pūnaewele i hoʻokaʻawale ʻia.

Kīkoʻo

Nā kelepona uku, nā hoʻopaʻa inoa hoʻopaʻa inoa, a me nā leo o ka pākaukau kūʻai i hoʻokō ʻia ma ka pūnaewele.

Ka uku

Kīwī kīwī

$499/no

ʻO kāu mea hoʻohana GPU ponoʻī. ʻAʻole e haʻalele ka leo i kāu hana hana. ʻO ka pilikino end-to-end maoli.

  • Hoʻolauna ʻia ka A100 GPU
  • Hoʻokaʻawale server -ʻaʻohe hoʻokumu i hoʻokaʻawaleʻia
  • Hoʻokō ʻia ka leo ma kāu kamepiula wale nō
  • Hoʻopili piha API + SLA
  • Nā minuke kāhea

Ka Mana Hoʻokipa

$99/no

Hoʻokō i STT.ai ma kāu pono pono'ī. Docker image, kāu mau mea lawelawe, kāu mau kānāwai.

  • Ke kiʻi Docker - e holo ana ma kekahi NVIDIA GPU
  • Hoʻohana ʻia ka hoʻohana ʻana i ka ʻōnaehana Air-gapped — ʻaʻohe pūnaewele e pono ai
  • Hoʻohui ʻia nā hoʻohou hōʻailona
  • Ka mana piha ma luna o kouʻike
  • Nā minuke kāhea

E hoʻomākaukau e hoʻokele i kāu hana hana hoʻololi?

E haʻi mai iā mākou e pili ana i kāu mau pono. E kōkua mākou iā ʻoe e koho i ka koho hoʻouka kūpono.

Get Started

Nā nīnau i nīnau pinepine ʻia

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.
Mahalo!
He aha kou mau ʻike?