Try it now, no signup
Upload a file, record live, paste a link, or import from your cloud, then watch it transcribe.
The RealtimeVoiceKIT API drops speech-to-text directly into your application. Submit a file or URL, receive predictable JSON with words, timestamps, confidence, and speaker labels, and get notified by webhook when a job finishes, no polling, no infrastructure to manage.
Build with it
SaaS products
Add transcription and captions to your own app or platform.
Media pipelines
Automate captioning and translation at scale.
Voice & meeting tools
Generate transcripts and summaries from recordings.
Internal automation
Turn call and meeting audio into structured data.
Developer features
How it works
Create a key
Generate an rtvk_ API key from your dashboard in seconds.
Submit a job
POST a file or URL to the API and start a transcription job.
Receive results
Get notified by webhook and fetch structured JSON results.
Frequently asked questions
How do I authenticate with the API?
Each request uses an rtvk_ API key you generate from your dashboard. Keys are scoped to your account and can be rotated anytime.
Does the API support webhooks?
Yes. Submit a job and RealtimeVoiceKIT calls your webhook when it finishes, no polling required.
What does the API return?
Predictable JSON with the transcript text, word-level timestamps, confidence scores, and speaker labels, plus subtitle and translation output.
Which plans include API access?
The Developer API is pay-per-minute, every account gets 10 free minutes, then $0.005 per minute, with no plan required. You can start free to evaluate transcription quality first.