Local transcription
Audio is transcribed locally with Whisper-based models.
Free alpha · Windows · Local-first · Azure optional
Speech to text for teams that need clear data boundaries.
Skald is a local-first speech-to-text and transcription app for Windows. Audio can be processed on the device by default. When cloud processing is needed, Skald can use Azure AI Foundry through your organization’s own endpoint.
- No telemetry
- Optional: your Azure endpoint
- Clear account-based Desktop access
Data boundary
Process locally. Extend deliberately.
Skald separates local transcription, cloud transcription, and optional text polishing into clear processing modes. Cloud processing is only used when configured through your organization’s Azure AI Foundry endpoint.
Azure cloud transcription
Audio is sent to your Azure AI Foundry transcription endpoint.
Local + Azure polish
Audio stays local. Only transcript text is optionally sent for conservative cleanup.
Azure + Azure polish
Cloud transcription and polishing both run through your Azure endpoint.
Product
Built for daily speech-to-text workflows.
The interface is practical: record, review, save, and continue working.
Current status
Free alpha for evaluation and pilots.
Skald is available for evaluation and pilot feedback while distribution, installer experience, and enterprise operations are hardened.
- Local Whisper-based speech to text
- Push-to-talk and toggle recording
- Optional Azure processing through your endpoint
- Account-based access to Skald for Windows