2025-04-04 Benchmarks

Computing time benchmarks

Welcome to the Voice Harbor API documentation.

Learn how to transcribe a pre-recorded audio file while removing PHI.

Learn how to transcribe a pre-recorded audio file using the Voice Harbor's Python SDK, while removing PHI.

Learn how to replace a pre-existing identity in audio file using the Voice Harbor's Python SDK, while preserving Emotion and Phonetic information.

Context-aware PHI redaction. Multilingual, fast and efficient.

Manage tokens, oversee configurations, and monitor system usage

Efficent separation for noisy medical condition.

Creates a new job on the Voice Harbor API after verifying the usage token.

Retrieves a list of jobs associated with the authenticated token.

Returns a signed URL for submitting your file and job to the Voice Harbor API.

Returns a signed URL for downloading results from the Voice Harbor API.

Retrieves all content items for a given job.

Creates a new developer token mapped to the provided admin token.

Retrieves all developer tokens associated with the provided admin token.

Config	Start Time	End Time	Duration
PHI redaction “advanced”	2025-04-04 06:36:08	2025-04-04 06:39:17	~3 min 9 sec (189 sec)
PHI redaction “mini”	2025-04-04 06:40:56	2025-04-04 06:42:22	~1 min 26 sec (86 sec)
Transcription	2025-04-04 06:46:50	2025-04-04 06:47:35	~45 sec