Skip to main content
OpenWhispr gives you four ways to process speech. Pick the one that fits your workflow.

OpenWhispr Cloud

Sign in with Google, Apple (macOS), Microsoft, or email — no API keys needed.
  • Free plan — 2,000 words/week with a 7-day Pro trial for new accounts
  • Pro plan — unlimited transcriptions
  • Fastest option, no model downloads
  • Audio is processed on OpenWhispr’s servers

Bring your own key (BYOK)

Use your own API keys from third-party providers:
ProviderWhat you get
OpenAITranscription plus GPT models for AI actions
GroqFast Whisper transcription plus hosted reasoning models
xAIGrok speech-to-text
MistralVoxtral transcription model
TinfoilConfidential, attested transcription (realtime and uploaded audio)
CortiClinical-grade transcription plus EU-hosted AI cleanup and reasoning
OpenRouter300+ AI agent and text-enhancement models through one key
Anthropic / Google GeminiAI agent and text enhancement models
Enter your API keys in Settings under each provider section.

Enterprise

Point OpenWhispr at your organization’s cloud LLM account — no personal API keys, no proxy. Credentials resolve through the standard cloud SDK chain (SSO, assumed roles, env vars).
  • AWS Bedrock — generally available
  • Azure OpenAI and GCP Vertex AI — coming soon
See enterprise providers for setup.

Local processing

Download a model and process everything on your device. Audio never leaves your machine.
  • Whisper — multiple model sizes from 75 MB to 3 GB
  • NVIDIA Parakeet — fast multilingual model (~680 MB)
  • Works offline after initial model download
  • See local models for setup

Comparison

CloudBYOKEnterpriseLocal
SetupSign inAdd API keyConfigure cloud credentialsDownload model
SpeedFastFastFastDepends on model
PrivacyAudio sent to serversAudio sent to providerAudio sent to your cloud accountFully private
InternetRequiredRequiredRequiredNot needed
CostFree tier or Pro planYour provider’s pricingYour cloud account’s pricingFree