Command-line interface¶
The CLI is installed with the package and is invoked as cobalstamp.
As with the Python API, it requires the COBALSTAMP_KEY environment
variable (Environment variables) and a network connection.
Audio files¶
The CLI reads and writes standard uncompressed WAV files, mono or multi-channel, at any sampling rate. The marked audio is written with the same channel layout as the input.
Marking¶
cobalstamp mark input.wav --output marked.wav --not-ai
The mark command marks the input audio file, registers the mark on
the server, and writes the marked audio to the output file. The flags
follow cobalstamp.mark():
--is-ai/--not-ai(exactly one is required): declare that the audio is created using AI, or not.--ai-type generated|transformed(optional): the AI type, when--is-ai.--clip compress|rescale|none(defaultcompress): protects the marked audio from exceeding full scale.
The command prints the mark info as a single JSON document on stdout, in
the same shape as the one returned by cobalstamp.mark():
{
"marked": true,
"mark_id": "eac8d9d9-c918-442b-b66c-13b1170ab2b3"
}
Detection¶
cobalstamp detect input.wav
The detect command looks for a registered Cobalstamp watermark in
the input audio file and prints the server’s verdict as a single JSON
document on stdout, or to the file given with -o. The verdict has
the same shape as the one returned by cobalstamp.detect():
{
"marked": true,
"mark_id": "eac8d9d9-c918-442b-b66c-13b1170ab2b3",
"is_ai": false,
"ai_type": null,
"ppid": "8JKH-A5VH-6DPD-M73L"
}
Forgetting test marks¶
cobalstamp forget <mark_id>
cobalstamp forget all
The forget command forgets a registered test mark, freeing the
marked audio so it can be marked again. It prints the number of
forgotten test marks on stdout, as cobalstamp.forget() does.
Exit codes¶
0: success.1: a runtime error occurred (unreadable audio file, server error, network failure); a one-line message is printed on stderr.2: invalid command-line arguments.