Encrypted in transit and at rest
API traffic is TLS-secured, and stored audio, transcripts, and metadata are encrypted at rest.
OpenAI's Whisper API (whisper-1) takes files up to 25 MB and leaves speaker labels to a separate model. The WhisperAI API is built for real recordings: send audio or video up to 5 GB, or a URL, and get speaker labels, word-level timestamps and a webhook when the transcript is ready.
# Start a transcript from any public audio URL curl https://api.whisperai.com/v1/transcript \ -H "Authorization: wai_your_api_key_here" \ -H "Content-Type: application/json" \ -d '{"audio_url":"https://example.com/meeting.mp3","speaker_labels":true}'
Both turn speech into text. These are the limits developers run into first with whisper-1.
OpenAI Whisper APIUp to 25 MB. Larger recordings have to be compressed or split into chunks.
WhisperAI APIUp to 5 GB per file, or pass a public audio_url and skip the upload.
OpenAI Whisper APINot on whisper-1. OpenAI offers them through a separate model, gpt-4o-transcribe-diarize.
WhisperAI APISet speaker_labels to true on the same request.
OpenAI Whisper APIYes, with timestamp_granularities.
WhisperAI APIYes. Every word comes back with its start and end time.
OpenAI Whisper APIInto English only.
WhisperAI APIInto up to 86 target languages, as an add-on once the transcript is done.
Why developers choose WhisperAI for production transcription workflows.
“We deleted our in-house Whisper cluster and replaced it with a single endpoint — same accuracy, a fraction of the ops.”
“Word-level timestamps and speaker labels in one response saved us weeks of post-processing. The docs are excellent.”
“Webhooks made our async pipeline trivial. We went from prototype to production in a single afternoon.”
Production-ready transcription features through one simple API.
Separate speakers automatically and return each turn with the transcript.
Every word and segment carries start/end times — perfect for captions, search, and clipping.
Stream live speech with low-latency results across 18 supported languages.
Return clean transcript, speaker, and timing data ready for your application.
Automatically detect and transcribe prerecorded audio across more than 100 languages.
Async jobs with webhook callbacks so your app can react when transcription completes.
Simple API. Structured results. Test the workflow in the Developer Portal before you ship.
Send a public audio URL, or upload your file first, to create a transcript job.
POST/v1/transcriptTrack status, or let a webhook notify you the moment processing completes.
GET/v1/transcript/{id}Retrieve full text, timestamps, speaker turns, subtitles, and derived views.
GET/v1/transcript/{id}/sentences# Create a transcript from a public audio URL curl https://api.whisperai.com/v1/transcript \ -H "Authorization: wai_your_api_key_here" \ -H "Content-Type: application/json" \ -d '{"audio_url":"https://example.com/meeting.mp3","speaker_labels":true}'
Supports audio and video files up to 5GB, plus realtime and translation APIs.
Protect customer data with encrypted transport and storage, private account access, and revocable API keys.
API traffic is TLS-secured, and stored audio, transcripts, and metadata are encrypted at rest.
Uploaded files remain private to your API account, and transcripts can be deleted through the API.
Create and revoke API keys from the Developer Portal, and keep secret keys on your server.
Start pay as you go or choose Developer for included pre-recorded minutes. Realtime and translation are metered separately on both plans.
| Pay as you go | Developer | |
|---|---|---|
| Pre-Recorded Audio | ||
| Price | $0.01 / minute | $99 / month |
| Included Minutes | - | 10,000 / month |
| Additional Usage | $0.01 / minute | $0.006 / minute |
| REST API | Included | Included |
| Concurrency limit | Up to 250 concurrent requests | Up to 250 concurrent requests |
| Languages | 100+ | 100+ |
| Speaker Labels | Included | Included |
| Timestamps | Included | Included |
| File size limit | 5GB / 10 hours | 5GB / 10 hours |
| Realtime Speech-to-Text | ||
| Price | $0.0067 / minute | $0.0067 / minute |
| Streaming API | Included | Included |
| Realtime Results | Included | Included |
| Languages | 18 | 18 |
| Speaker Labels | Included | Included |
| Translation | ||
| Price | $0.001 / minute / language | $0.0005 / minute / language |
| Availability | Included | Included |
| Target Languages | 87 | 87 |
| Speaker Labels Preserved | Included when speaker labels are enabled on the source transcript | Included when speaker labels are enabled on the source transcript |
| Multiple Languages Per Request | Included | Included |
| Create account | Choose Developer | |
Translation is billed separately from transcription. Speaker labels are preserved in translated utterances when they were enabled on the source transcript.
Everything you need to know about building on the WhisperAI API.
Copy-paste examples in cURL, Python, and Node. Full API reference and an in-dashboard playground to test before you ship.
Open documentationCreate an account, then continue straight to the Developer Portal.