Skip to navigation

Detect Watermark

Beta
View as Markdown

Beta. Detects whether an audio clip carries the Sarvam STFT watermark embedded by Instant Voice Cloning generation.

Upload a clip produced by POST /voices/clone (or stream / WebSocket) to check whether Sarvam generated it. Clips shorter than about 5 seconds usually return inconclusive — there is not enough signal to be confident.

Accepts multipart/form-data with a single file upload.

Base URL: https://api.sarvam.ai. Auth: send your key in the api-subscription-key header.

Limits: max file size 10 MB; analysis is capped at 120 seconds of audio. Rate limited to 5 requests per minute.

Billing: free — this endpoint consumes no credits.

Authentication

api-subscription-keystring
API Key authentication via header

Request

This endpoint expects a multipart form containing a file.
filefileRequired
Audio clip to analyse. Supported formats include WAV, MP3, FLAC, OGG, M4A, and WebM. Max file size 10 MB. Analysis uses at most the first 120 seconds.

Response

Detection completed.
statusstring

success

dataobject

Errors

400
Bad Request Error
401
Unauthorized Error
429
Too Many Requests Error
500
Internal Server Error