gcloud alpha ml video transcribe-speech

NAME: gcloud alpha ml video transcribe-speech - transcribe speech in a video
SYNOPSIS: gcloud alpha ml video transcribe-speech INPUT_PATH --language-code=LANGUAGE_CODE [--async] [--audio-tracks=[AUDIO_TRACKS,…]] [--diarization-speaker-count=DIARIZATION_SPEAKER_COUNT] [--enable-automatic-punctuation] [--enable-speaker-diarization] [--enable-word-confidence] [--filter-profanity] [--hints=[HINTS,…]] [--max-alternatives=MAX_ALTERNATIVES] [--output-uri=OUTPUT_URI] [--region=REGION] [--segments=[SEGMENTS,…]] [GCLOUD_WIDE_FLAG …]
DESCRIPTION: (ALPHA) Transcribe speech within a video.
EXAMPLES: To transcribe speech in video file 'gs://my_bucket/input_file.mp4':
gcloud alpha ml video transcribe-speech gs://my_bucket/input_file.mp4
POSITIONAL ARGUMENTS: INPUT_PATH

Path to the video to be analyzed. Must be a local path or a Google Cloud Storage URI.
REQUIRED FLAGS: --language-code=LANGUAGE_CODE

The language of the supplied audio as a BCP-47 language tag. Example: "en-US". See Language Support for a list of the currently supported language codes.
OPTIONAL FLAGS: --async

Return immediately, without waiting for the operation in progress to complete.

--audio-tracks=[AUDIO_TRACKS,…]

For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two commas separated tracks. Default track is 0.

--diarization-speaker-count=DIARIZATION_SPEAKER_COUNT

Optional estimated number of speakers in the conversation. If not specified, defaults to '2'. Ignored unless --enable-speaker-diarization is enabled.

--enable-automatic-punctuation

If enabled, adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default disabled case does not add punctuation to result hypotheses.

--enable-speaker-diarization

If enabled, perform speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo results section. When this is enabled, we send all the words from the beginning of the audio for the top alternative in every consecutive responses. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time.

--enable-word-confidence

If enabled, the top result includes a list of words and the confidence for those words. If disabled, no word-level confidence information is returned. The default is disabled.

--filter-profanity

If enabled, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. f***. If disabled or omitted, profanities will not be filtered out.

--hints=[HINTS,…]

list of strings containing words and phrases "hints" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See (https://cloud.google.com/speech/limits#content).

--max-alternatives=MAX_ALTERNATIVES

Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of SpeechRecognitionAlternative messages within each SpeechTranscription. The server may return fewer than max_alternatives. Valid values are 0-30. A value of 0 or 1 will return a maximum of one. If omitted, will return a maximum of one

--output-uri=OUTPUT_URI

Location to which the results should be written. Must be a Google Cloud Storage URI.

--region=REGION

Optional Cloud region where annotation should take place. If no region is specified, a region will be determined based on video file location. REGION must be one of: asia-east1, europe-west1, us-east1, us-west1.

--segments=[SEGMENTS,…]

Segments from the video which you want to analyze (by default, the entire video will be treated as one segment). Must be in the format START1:END1[,START2:END2,…] (inclusive). START and END of segments must be a properly formatted duration string of the form HhMmSs where:
* H is the number of hours from beginning of video * M is the number of minutes from the beginning of video * S is the number of seconds from the beginning of the video

H, M and S can be specified as ints or floats for fractional units (to microsecond resolution). Unit chars (e.g. h, m or s) are required. Microseconds can be specified using fractional seconds e.g. 0.000569s == 569 microseconds.
Examples:
0s:23.554048s,24s:29.528064s
0:1m40s,3m50s:5m10.232265s
GCLOUD WIDE FLAGS: These flags are available to all commands: --access-token-file, --account, --billing-project, --configuration, --flags-file, --flatten, --format, --help, --impersonate-service-account, --log-http, --project, --quiet, --trace-token, --user-output-enabled, --verbosity.
Run $ gcloud help for details.
API REFERENCE: This command uses the videointelligence/v1 API. The full documentation for this API can be found at: https://cloud.google.com/video-intelligence/docs/
NOTES: This command is currently in alpha and might change without notice. If this command fails with API permission errors despite specifying the correct project, you might be trying to access an API with an invitation-only early access allowlist. This variant is also available:
gcloud beta ml video transcribe-speech