Skip to main content
WhisperAI
Powered byOpenAI
FeaturesHow it worksPricingFAQDocs
Official WhisperAI.com API · v1

The Only Whisper API Built for Developers

Go beyond basic Whisper transcription with audio and video files up to 5GB, speaker labels, word-level timestamps, realtime speech-to-text, translation, and webhooks — all through one API.

Get your API key Read the docs
5GB audio & video·Speaker labels + timestamps·Realtime API
transcribe.sh
# 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}'
200 OK { "id": "tr_8fK2…", "status": "queued",
  "audio_url": "https://example.com/meeting.mp3" }
Loved by developers

Teams ship voice features faster

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.”
AEngineering LeadB2B SaaS platform
“Word-level timestamps and speaker labels in one response saved us weeks of post-processing. The docs are excellent.”
MStaff EngineerMedia & podcasting
“Webhooks made our async pipeline trivial. We went from prototype to production in a single afternoon.”
SFounderDeveloper tools startup
Capabilities

Everything you need to ship voice features

Production-ready transcription features through one simple API.

Speaker labels

Separate speakers automatically and return each turn with the transcript.

Word-level timestamps

Every word and segment carries start/end times — perfect for captions, search, and clipping.

Realtime transcription

Stream live speech with low-latency results across 18 supported languages.

Structured JSON

Return clean transcript, speaker, and timing data ready for your application.

100+ prerecorded languages

Automatically detect and transcribe prerecorded audio across more than 100 languages.

Webhooks

Async jobs with webhook callbacks so your app can react when transcription completes.

How it works

From audio to transcript in a few steps

Simple API. Structured results. Test the workflow in the Developer Portal before you ship.

  1. 1

    Create a transcript

    Send a public audio URL, or upload your file first, to create a transcript job.

    POST/v1/transcript
  2. 2

    Poll or get callback

    Track status, or let a webhook notify you the moment processing completes.

    GET/v1/transcript/{id}
  3. 3

    Use structured results

    Retrieve full text, timestamps, speaker turns, subtitles, and derived views.

    GET/v1/transcript/{id}/sentences
Developer PortalAPI playground
Open playground
API example views
# 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.

Security & privacy

Built for production, secure by default

Protect customer data with encrypted transport and storage, private account access, and revocable API keys.

Encrypted in transit and at rest

API traffic is TLS-secured, and stored audio, transcripts, and metadata are encrypted at rest.

Your data stays yours

Uploaded files remain private to your API account, and transcripts can be deleted through the API.

Secure API access

Create and revoke API keys from the Developer Portal, and keep secret keys on your server.

Pricing

Simple, usage-based pricing

Start pay as you go or choose Developer for included pre-recorded minutes. Realtime and translation are metered separately on both plans.

WhisperAI Developer API pricing and feature comparison
Pay as you goDeveloper
Pre-Recorded Audio
Price$0.01 / minute$99 / month
Included Minutes-10,000 / month
Additional Usage$0.01 / minute$0.006 / minute
REST APIIncludedIncluded
Concurrency limitUp to 250 concurrent requestsUp to 250 concurrent requests
Languages100+100+
Speaker LabelsIncludedIncluded
TimestampsIncludedIncluded
File size limit5GB / 10 hours5GB / 10 hours
Realtime Speech-to-Text
Price$0.01667 / minute$0.01667 / minute
Streaming APIIncludedIncluded
Realtime ResultsIncludedIncluded
Languages1818
Speaker LabelsIncludedIncluded
Translation
Price$0.001 / minute / language$0.0005 / minute / language
AvailabilityIncludedIncluded
Target Languages8787
Speaker Labels PreservedIncluded when speaker labels are enabled on the source transcriptIncluded when speaker labels are enabled on the source transcript
Multiple Languages Per RequestIncludedIncluded
Create accountChoose Developer

Translation is billed separately from transcription. Speaker labels are preserved in translated utterances when they were enabled on the source transcript.

FAQ

Frequently asked questions

Everything you need to know about building on the WhisperAI API.

Documentation

Built for developers, documented end to end.

Copy-paste examples in cURL, Python, and Node. Full API reference and an in-dashboard playground to test before you ship.

Open documentation
QuickstartYour first transcription in 5 minutes→API referenceEvery endpoint, parameter & response→ExamplescURL · Python · Node→PlaygroundTest the API right in your browser→

Start transcribing today.

Create an account, then continue straight to the Developer Portal.

Get your API key
WhisperAI
Powered byOpenAI

Speech intelligence for developers. Transcription is billed by the minute; translation is billed by minute and target language.

Product

FeaturesPricingPlaygroundChangelog

Developers

DocumentationAPI referenceExamplesStatus

Company

BlogHelp CenterSecurityContact
© 2026 WhisperAI, Inc.Developer API · v1