macOS
Universal DMG for Apple Silicon and Intel
Built by a team that has worked with global media, research, and Fortune 500 companies
Join 100k+ users across the web
SMSarah M.Podcast ProducerDCDavid C.Newsroom EditorERElena R.LocalizationMWMarcus W.Indie DevAKAisha K.Course CreatorTBTom B.JournalistPNPriya N.UX ResearcherLOLiam O.FilmmakerNHNoor H.ParalegalKTKenji T.LecturerMGMaya G.ClinicianRPRavi P.Product MgrSMSarah M.Podcast ProducerDCDavid C.Newsroom EditorERElena R.LocalizationMWMarcus W.Indie DevAKAisha K.Course CreatorTBTom B.JournalistPNPriya N.UX ResearcherLOLiam O.FilmmakerNHNoor H.ParalegalKTKenji T.LecturerMGMaya G.ClinicianRPRavi P.Product Mgr
Live demo
Hear it for yourself in seconds
Record straight from your mic or drop in a file. No account needed, save it to your account when you're ready.
Try it now, no signup
Upload a file, record live, paste a link, or import from your cloud, then watch it transcribe.
Any source
Transcribe from anywhere
Paste a link from YouTube, TikTok, Instagram, and more. We download the audio and transcribe it with speaker labels, subtitles, and translation. Nothing to upload.
Complete toolkit
Everything you need to turn audio into text, built in
From the first upload to publish-ready captions and translations, one workflow, nothing bolted on.
Explore all featuresAny sourceUpload, record, paste a link, or cloud import
Speaker labelsDiarization with editable names
Word confidencePer-word accuracy you can trust
100+ languagesTranscribe and translate in one pass
SubtitlesSRT, VTT, TXT, DOCX, PDF & JSON
AI built inSummaries, chat & sentiment on every file
Everything in one place
From raw audio to polished output
A complete AI transcription and translation toolkit, accurate, fast, and ready for production.
State-of-the-art AI accuracy
Whisper VoiceKit speech models tuned for accents, jargon, and noisy rooms, so you spend less time fixing transcripts.
- Robust to background noise & crosstalk
- Smart punctuation and casing
- Per-segment confidence scores
99.2%99.2%
AI speaker diarization
Automatically detects who said what and labels every speaker, even on overlapping conversations.
- Automatic speaker detection
- Editable speaker names across the file
- Works on interviews, panels & calls
S1
S2
100+ language AI translation
Transcribe in one language and translate to another in a single pass, with formatting preserved.
- 100+ supported languages
- Timing-preserving translation
- Keep versions side-by-side
ENES+100
How it works
Three steps to a finished transcript
No setup, no manual cleanup. Bring a file, leave with publish-ready text and captions.
01
Upload
Drag in audio or video, MP3, WAV, M4A, MP4 and more. Or paste a link or call the API.
↑MP3 · MP4 · URLinterview.mp3
02
Transcribe
Our Whisper VoiceKit engine processes your file, separates speakers, and produces a clean, time-coded transcript.
S1
03
Translate & export
Translate to 100+ languages, then export TXT, SRT, VTT, DOCX or PDF, or pull results via API.
EN→ES · FR · DE
TXTSRTVTT
Built for your workflow
One tool, many use cases
However you work with audio, RealtimeVoiceKit fits in.
Podcasters & creators
Podcasts · YouTube · Social
Repurpose episodes into show notes, blog posts, and captioned clips that rank and reach more people.
- One-click show notes & summary
- Auto-captioned vertical clips
- Translate captions for every platform
- Searchable archive of every episode
Host
Show notesCaptioned clipsAI summaries
Loved by creators & teams
What our customers say
Thousands of podcasters, journalists, and developers use RealtimeVoiceKit every day.
“We cut our editing time in half. The speaker labels are scarily accurate, and the subtitle export drops straight into our workflow.”
SM
Sarah M.
Podcast Producer
“Turnaround that used to take a freelancer a full day now takes minutes. Transcripts are clean enough to publish with light edits.”
DC
David C.
Newsroom Editor
“The API was a two-line integration. Webhooks instead of polling mean I never wrote a single retry loop.”
MW
Marcus W.
Indie Developer
Pricing
Simple plans that scale with you
Start free, upgrade when you need more minutes and translation.
Medical Mode
Transcription built for clinical vocabulary
Turn on Medical Mode for sharper accuracy on medications, procedures, conditions, and dosages, available in English, Spanish, German, and French.
- Medical speech model
- Confidence scores to review
- Free on every plan
Review transcripts before clinical use.
Security and privacy
Your audio stays private and protected
RealtimeVoiceKIT is built to protect your recordings, transcripts, and account, with encryption, granular consent, and full control over your data.
Encrypted in transit and at rest
TLS in transit and encryption at rest, with bcrypt-hashed passwords and hashed API keys.
You stay in control
Export your data or delete your account anytime. We never sell your data or train models on your content.
Consent and GPC respected
Granular cookie consent, and we honor Global Privacy Control as an automatic opt-out.
GDPR and CCPA ready
We support your data rights under GDPR and CCPA, with a Data Processing Addendum and a published list of sub-processors.
Mac, Windows, and Linux apps available
Transcribe from your desktop
Download RealtimeVoiceKIT for macOS, Windows, or Linux. Capture your microphone and supported system audio, transcribe in real time, and keep every session synced with the web.
Explore the desktop app
Free to download. Sign in with the same RealtimeVoiceKIT account you use on the web.
Android and iOS apps available
Take RealtimeVoiceKIT anywhere
RealtimeVoiceKIT is available on Google Play and the App Store. Record, transcribe, summarize, translate, and export subtitles from Android, iPhone, or iPad.
- Record, upload, and transcribe on the go
- AI summaries, subtitles, and translation
- Synced with your web account
Download RealtimeVoiceKIT from Google Play or the App Store and sign in with the same account you use on the web.
Available now
Transcribe any tab with the browser extension
Capture Google Meet calls, webinars, or any browser tab, record your microphone in one tap, and dictate in real time. Every session lands in your RealtimeVoiceKIT library with an AI summary.
- Live-transcribe any tab, no meeting bot required
- One-tap voice notes and real-time dictation
- AI summaries, translation, and subtitle export
Install it now from the Chrome Web Store. Works on Chrome and Edge.
Frequently asked questions
What is RealtimeVoiceKIT?
RealtimeVoiceKIT is an AI transcription and translation platform. Upload audio or video and get an accurate, speaker-labeled transcript with subtitles, plus optional translation into 100+ languages, through the web app or a developer API. Under the hood, transcription runs on Whisper VoiceKit speech models.
What audio and video files can I upload?
Common formats including MP3, WAV, M4A, and MP4 work out of the box. You can also transcribe from a URL or send files programmatically through the API.
How many languages do you support?
We transcribe and translate across 100+ languages, so you can caption and localize content for a global audience in a single workflow.
Can I export subtitles?
Yes. Every transcript can be exported as plain text, timestamped text, SRT, or WebVTT, ready for any video player or editing suite.
Is there a free plan?
Yes. The Free plan includes 10 minutes of transcription every month with speaker labels and subtitle export, no credit card required.
Do you have an API for developers?
Yes. Premium and Pro plans include a REST API with rtvk_ keys and webhooks, so you can add transcription, subtitles, and translation directly to your own product.
Get started
Start transcribing with AI in minutes
Get 10 free minutes every month. No credit card, no setup, just upload and go.
No credit card10 free minutes / monthCancel anytime
interview-final.mp398% confidence
Speaker 1
Welcome back to the show, today we're talking about real-time audio.
Speaker 2
Thanks for having me. The accuracy on technical terms has come a long way.
TranslateExport SRTSummary