werk1112

Audio CLI commands and options

Build scope: canonical Linux, --no-default-features, no optional backend features. Coverage is limited to this parser/schema profile, not every platform or feature build. See conditional build options for extensions.

Generated from werk 1.10.2. See CLI semantics, media input and override rules, and the canonical parameter schema.

Every command below also accepts global options and --help. Each command lists its additional accepted options; the catalogue below gives their syntax and meaning. A parsed flag does not imply that a particular model/backend implements it.

Commands

werk audio

Generate, understand, analyze, and transform audio

werk audio [OPTIONS] <COMMAND>

Subcommands: werk audio generate, werk audio transcribe, werk audio translate, werk audio detect, werk audio analyze, werk audio transform, werk audio embed.

werk audio generate

Generate speech, music, or sound

werk audio generate [OPTIONS] [MODEL] [COMMAND]

Subcommands: werk audio generate speech, werk audio generate music, werk audio generate sound.

Arguments:

[MODEL]

Additional options:

werk audio transcribe

Transcribe speech

werk audio transcribe [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio translate

Translate speech into English

werk audio translate [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio detect

Detect events, voice activity, speakers, language, or emotion

werk audio detect [OPTIONS] <COMMAND>

Subcommands: werk audio detect event, werk audio detect voice, werk audio detect speaker, werk audio detect language, werk audio detect emotion.

werk audio analyze

Caption, diarize, classify, or understand audio

werk audio analyze [OPTIONS] <COMMAND>

Subcommands: werk audio analyze caption, werk audio analyze diarize, werk audio analyze classify, werk audio analyze understand.

werk audio transform

Convert, separate, enhance, or edit audio

werk audio transform [OPTIONS] <COMMAND>

Subcommands: werk audio transform voice, werk audio transform separate, werk audio transform enhance, werk audio transform edit.

werk audio embed

Create an embedding for an audio recording

werk audio embed [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio generate speech

Synthesize speech from text

werk audio generate speech [OPTIONS] <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio generate music

Generate music or a song

werk audio generate music [OPTIONS] <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio generate sound

Generate a sound effect or general-purpose audio

werk audio generate sound [OPTIONS] <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio detect event

Detect acoustic events

werk audio detect event [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio detect voice

Detect speech or voice activity

werk audio detect voice [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio detect speaker

Identify a speaker

werk audio detect speaker [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio detect language

Identify the spoken language

werk audio detect language [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio detect emotion

Recognize emotion in speech

werk audio detect emotion [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio analyze caption

Caption an audio recording

werk audio analyze caption [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio analyze diarize

Diarize speakers in a recording

werk audio analyze diarize [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio analyze classify

Classify an audio recording

werk audio analyze classify [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio analyze understand

Analyze or answer a prompt about audio

werk audio analyze understand [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio transform voice

Convert a voice using an optional reference

werk audio transform voice [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio transform separate

Separate audio into stems

werk audio transform separate [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio transform enhance

Enhance or restore audio

werk audio transform enhance [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

werk audio transform edit

Edit audio from a text instruction

werk audio transform edit [OPTIONS] --input <AUDIO> <MODEL>

Arguments:

<MODEL>

Additional options:

Option catalogue

Syntax ending in ... accepts repeated values. List controls also accept repeated occurrences of their flag. Boolean pairs inherit when omitted; positive and negative flags conflict. Schema defaults, units, types and task applicability are in the linked parameter table.

--accelerator

--accelerator <ACCELERATOR>

Requested accelerator, for example cpu, cuda, rocm, metal, or auto

--accent

--accent <ACCENT>

Accent (runtime/model-defined control); string tts.accent.

--acoustic-electronic-balance

--acoustic-electronic-balance <ACOUSTIC_ELECTRONIC_BALANCE>

Acoustic electronic balance (runtime/model-defined control); number audio.acoustic_electronic_balance.

--allow-component-offload

--allow-component-offload

Permit component offload when GPU memory is insufficient and projected host RAM fits

--allow-cpu-offload

--allow-cpu-offload

Permit model CPU offload when GPU memory is insufficient and the projected host-RAM requirement fits

--allow-disk-offload

--allow-disk-offload

Allow disk-backed model offloading; boolean routing.allow_disk_offload.

--allow-sequential-offload

--allow-sequential-offload

Permit slower sequential CPU offload when GPU memory is insufficient and projected host RAM fits

--arrangement-prompt

--arrangement-prompt <ARRANGEMENT_PROMPT>

Arrangement prompt (runtime/model-defined control); string audio.arrangement_prompt.

--articulation

--articulation <ARTICULATION>

Articulation (runtime/model-defined control); number audio.articulation.

--attention-backend

--attention-backend <ATTENTION_BACKEND>

Requested attention implementation

--audio-strength

--audio-strength <AUDIO_STRENGTH>

Audio strength (runtime/model-defined control); number audio.audio_strength.

--backing-vocals

--backing-vocals

Backing vocals (runtime/model-defined control); boolean audio.backing_vocals.

--bass-instrument

--bass-instrument <BASS_INSTRUMENT>

Bass instrument (runtime/model-defined control); string audio.bass_instrument.

--beam-size

--beam-size <BEAM_SIZE>

Beam search width; integer stt.beam_size.

--best-of

--best-of <BEST_OF>

Candidates sampled; integer stt.best_of.

--bit-depth

--bit-depth <BIT_DEPTH>

PCM output bit depth; integer audio.bit_depth.

--bitrate

--bitrate <BITRATE>

Bitrate (runtime/model-defined control); string audio.bitrate.

--bpm

--bpm <BPM>

Bpm (runtime/model-defined control); number audio.bpm.

--bpm-max

--bpm-max <BPM_MAX>

Tempo max (runtime/model-defined control); number audio.tempo_max.

--bpm-min

--bpm-min <BPM_MIN>

Tempo min (runtime/model-defined control); number audio.tempo_min.

--breathiness

--breathiness <BREATHINESS>

Breathiness (runtime/model-defined control); number audio.breathiness.

--channels

--channels <CHANNELS>

Output channel count; integer audio.channels; Output channels; integer tts.channels.

--choir-amount

--choir-amount <CHOIR_AMOUNT>

Choir amount (runtime/model-defined control); number audio.choir_amount.

--chord-audio

--chord-audio <PATH>

Chord audio (runtime/model-defined control); path audio.chord_audio.

--chord-complexity

--chord-complexity <CHORD_COMPLEXITY>

Chord complexity (runtime/model-defined control); number audio.chord_complexity.

--chord-progression

--chord-progression <CHORD_PROGRESSION>

Chord progression (runtime/model-defined control); string audio.chord_progression.

--chunk-size

--chunk-size <CHUNK_SIZE>

Chunk size (runtime/model-defined control); integer tts.chunk_size.

--codec

--codec <CODEC>

Codec (runtime/model-defined control); string audio.codec.

--compile

--compile

Explicitly enable runtime compilation

--condition-on-previous-text

--condition-on-previous-text

Condition on previous text (runtime/model-defined control); boolean stt.condition_on_previous_text.

--continuation-duration

--continuation-duration <SECONDS>

Continuation duration (runtime/model-defined control); number audio.continuation_duration.

--continuation-start

--continuation-start <SECONDS>

Continuation start (runtime/model-defined control); number audio.continuation_start.

--creativity

--creativity <CREATIVITY>

Creativity (runtime/model-defined control); number audio.creativity.

--debug

--debug

Print the resolved media request, routing candidates, and backend details

--descriptor

--descriptor <DESCRIPTORS>

Repeatable item for: Descriptors (runtime/model-defined control); list audio.descriptors.

--dialect

--dialect <DIALECT>

Dialect (runtime/model-defined control); string tts.dialect.

--diarization

--diarization

Identify speakers; boolean stt.diarization.

--duet

--duet

Duet (runtime/model-defined control); boolean audio.duet.

--duration

--duration <SECONDS>

Requested duration in seconds; number audio.duration.

--emotion

--emotion <EMOTION>

Emotion (runtime/model-defined control); string tts.emotion.

--emotion-strength

--emotion-strength <EMOTION_STRENGTH>

Emotion strength (runtime/model-defined control); number tts.emotion_strength.

--era

--era <ERAS>

Repeatable item for: Eras (runtime/model-defined control); list audio.eras.

--excluded-instrument

--excluded-instrument <EXCLUDED_INSTRUMENTS>

Repeatable item for: Excluded instruments (runtime/model-defined control); list audio.excluded_instruments.

--export-stems

--export-stems

Export stems (runtime/model-defined control); boolean audio.export_stems.

--expressiveness

--expressiveness <EXPRESSIVENESS>

Expressiveness (runtime/model-defined control); number tts.expressiveness.

--fallback-policy

--fallback-policy <FALLBACK_POLICY>

Fallback policy: none, backend, or degrade; degrade permits inherited memory-saving strategies

--format

--format <FORMAT>

Audio container; enumeration audio.output_format; Audio output format; enumeration tts.output_format.

--generate-lyrics

--generate-lyrics

Generate lyrics (runtime/model-defined control); boolean audio.generate_lyrics.

--genre

--genre <GENRES>

Repeatable item for: Genres (runtime/model-defined control); list audio.genres.

--guidance

--guidance <GUIDANCE>

Guidance (runtime/model-defined control); number audio.guidance.

--hallucination-silence-threshold

--hallucination-silence-threshold <HALLUCINATION_SILENCE_THRESHOLD>

Hallucination silence threshold (runtime/model-defined control); number stt.hallucination_silence_threshold.

--harmonic-tension

--harmonic-tension <HARMONIC_TENSION>

Harmonic tension (runtime/model-defined control); number audio.harmonic_tension.

--harmony-adherence

--harmony-adherence <HARMONY_ADHERENCE>

Harmony adherence (runtime/model-defined control); number audio.harmony_adherence.

--harmony-amount

--harmony-amount <HARMONY_AMOUNT>

Harmony amount (runtime/model-defined control); number audio.harmony_amount.

--hotword

--hotword <HOTWORDS>

Repeatable item for: Hotwords (runtime/model-defined control); list stt.hotwords.

--influence

--influence <INFLUENCES>

Repeatable item for: Influences (runtime/model-defined control); list audio.influences.

--initial-prompt

--initial-prompt <INITIAL_PROMPT>

Initial prompt (runtime/model-defined control); string stt.initial_prompt.

--input

--input <AUDIO>

Input audio (runtime/model-defined control); path stt.input_audio.

--instrument-density

--instrument-density <INSTRUMENT_DENSITY>

Instrument density (runtime/model-defined control); number audio.instrument_density.

--instrumental

--instrumental

Generate without vocals; boolean audio.instrumental.

--instrumental-audio

--instrumental-audio <PATH>

Instrumental audio (runtime/model-defined control); path audio.instrumental_audio.

--intimacy

--intimacy <INTIMACY>

Intimacy (runtime/model-defined control); number audio.intimacy.

--key

--key <KEY>

Key (runtime/model-defined control); string audio.key.

--language

--language <LANGUAGE>

Language (runtime/model-defined control); string stt.language; Language (runtime/model-defined control); string tts.language.

--lead-instrument

--lead-instrument <LEAD_INSTRUMENT>

Lead instrument (runtime/model-defined control); string audio.lead_instrument.

--loudness-lufs

--loudness-lufs <LOUDNESS_LUFS>

Loudness lufs (runtime/model-defined control); number audio.loudness_lufs; Loudness (runtime/model-defined control); number tts.loudness.

--lyrics

--lyrics <LYRICS>

Song lyrics

--lyrics-adherence

--lyrics-adherence <LYRICS_ADHERENCE>

Lyrics adherence (runtime/model-defined control); number audio.lyrics_adherence.

--lyrics-file

--lyrics-file <PATH>

Read song lyrics from a file

--lyrics-language

--lyrics-language <LYRICS_LANGUAGE>

Lyrics language (runtime/model-defined control); string audio.lyrics_language.

--max-new-tokens

--max-new-tokens <MAX_NEW_TOKENS>

Max new tokens (runtime/model-defined control); integer audio.max_new_tokens.

--max-speakers

--max-speakers <MAX_SPEAKERS>

Max speakers (runtime/model-defined control); integer stt.max_speakers.

--melody-adherence

--melody-adherence <MELODY_ADHERENCE>

Melody adherence (runtime/model-defined control); number audio.melody_adherence.

--melody-audio

--melody-audio <PATH>

Melody audio (runtime/model-defined control); path audio.melody_audio.

--min-speakers

--min-speakers <MIN_SPEAKERS>

Min speakers (runtime/model-defined control); integer stt.min_speakers.

--mood

--mood <MOODS>

Repeatable item for: Moods (runtime/model-defined control); list audio.moods.

--music-instrument

--music-instrument <SPEC>

Repeatable item for: Instruments (runtime/model-defined control); list audio.instruments.

--music-instrument-file

--music-instrument-file <PATH>

Load JSON from a UTF-8 file for: Instruments (runtime/model-defined control); list audio.instruments.

--music-instrument-json

--music-instrument-json <JSON>

Load JSON from the argument for: Instruments (runtime/model-defined control); list audio.instruments.

--music-mastering-control

--music-mastering-control <SPEC>

Repeatable item for: Mastering controls (runtime/model-defined control); list audio.mastering_controls.

--music-mastering-control-file

--music-mastering-control-file <PATH>

Load JSON from a UTF-8 file for: Mastering controls (runtime/model-defined control); list audio.mastering_controls.

--music-mastering-control-json

--music-mastering-control-json <JSON>

Load JSON from the argument for: Mastering controls (runtime/model-defined control); list audio.mastering_controls.

--music-mix-control

--music-mix-control <SPEC>

Repeatable item for: Mix controls (runtime/model-defined control); list audio.mix_controls.

--music-mix-control-file

--music-mix-control-file <PATH>

Load JSON from a UTF-8 file for: Mix controls (runtime/model-defined control); list audio.mix_controls.

--music-mix-control-json

--music-mix-control-json <JSON>

Load JSON from the argument for: Mix controls (runtime/model-defined control); list audio.mix_controls.

--negative-prompt

--negative-prompt <NEGATIVE_PROMPT>

Negative prompt text

--negative-prompt-file

--negative-prompt-file <PATH>

Read negative prompt text from a file

--no-allow-component-offload

--no-allow-component-offload

Forbid component offload

--no-allow-cpu-offload

--no-allow-cpu-offload

Forbid model CPU offload; an over-limit GPU plan fails unless another strategy is explicitly permitted

--no-allow-disk-offload

--no-allow-disk-offload

Explicitly disable: Allow disk-backed model offloading; boolean routing.allow_disk_offload.

--no-allow-sequential-offload

--no-allow-sequential-offload

Forbid sequential CPU offload

--no-backing-vocals

--no-backing-vocals

Explicitly disable: Backing vocals (runtime/model-defined control); boolean audio.backing_vocals.

--no-compile

--no-compile

Explicitly disable runtime compilation

--no-condition-on-previous-text

--no-condition-on-previous-text

Explicitly disable: Condition on previous text (runtime/model-defined control); boolean stt.condition_on_previous_text.

--no-diarization

--no-diarization

Explicitly disable: Identify speakers; boolean stt.diarization.

--no-duet

--no-duet

Explicitly disable: Duet (runtime/model-defined control); boolean audio.duet.

--no-export-stems

--no-export-stems

Explicitly disable: Export stems (runtime/model-defined control); boolean audio.export_stems.

--no-generate-lyrics

--no-generate-lyrics

Explicitly disable: Generate lyrics (runtime/model-defined control); boolean audio.generate_lyrics.

--no-instrumental

--no-instrumental

Explicitly disable: Generate without vocals; boolean audio.instrumental.

--no-normalization

--no-normalization

Explicitly disable: Normalization (runtime/model-defined control); boolean audio.normalization.

--no-normalize

--no-normalize

Explicitly disable: L2-normalize the embedding vector; boolean audio.normalize.

--no-phoneme-input

--no-phoneme-input

Explicitly disable: Phoneme input (runtime/model-defined control); boolean tts.phoneme_input.

--no-segment-timestamps

--no-segment-timestamps

Explicitly disable: Return segment timestamps; boolean stt.segment_timestamps.

--no-streaming

--no-streaming

Explicitly disable: Stream audio chunks when supported; boolean tts.streaming.

--no-vad

--no-vad

Explicitly disable: Vad (runtime/model-defined control); boolean stt.vad.

--no-vocals

--no-vocals

Explicitly disable: Vocals (runtime/model-defined control); boolean audio.vocals.

--no-word-timestamps

--no-word-timestamps

Explicitly disable: Return word timestamps; boolean stt.word_timestamps.

--normalization

--normalization

Normalization (runtime/model-defined control); boolean audio.normalization.

--normalize

--normalize

L2-normalize the embedding vector; boolean audio.normalize.

--num-stems

--num-stems <NUM_STEMS>

Num stems (runtime/model-defined control); integer audio.num_stems.

--num-variations

--num-variations <NUM_VARIATIONS>

Number of generated variations; integer audio.variations.

--originality

--originality <ORIGINALITY>

Originality (runtime/model-defined control); number audio.originality.

--output

--output <PATH>

Output file or directory; defaults to WERK_HOME/outputs with a generated name

--output-format

--output-format <OUTPUT_FORMAT>

Embedding result format; enumeration audio.output_format; Transcription output format; enumeration stt.output_format.

--parameter-policy

--parameter-policy <PARAMETER_POLICY>

Parameter support policy: strict, warn, or permissive

--pause-scale

--pause-scale <PAUSE_SCALE>

Pause scale (runtime/model-defined control); number tts.pause_scale.

--performance-preference

--performance-preference <PERFORMANCE_PREFERENCE>

Performance preference, for example speed, balanced, memory, or quality

--phoneme-input

--phoneme-input

Phoneme input (runtime/model-defined control); boolean tts.phoneme_input.

--pitch

--pitch <PITCH>

Pitch shift; number tts.pitch.

--pooling

--pooling <POOLING>

Frame pooling strategy; enumeration audio.pooling.

--precision

--precision <PRECISION>

Requested compute precision

--profile

--profile <PROFILE>

Stored or built-in execution profile

--prompt

--prompt <PROMPT>

Prompt text

--prompt-adherence

--prompt-adherence <PROMPT_ADHERENCE>

Prompt adherence (runtime/model-defined control); number audio.prompt_adherence.

--prompt-file

--prompt-file <PATH>

Read prompt text from a file

--pronunciation-dictionary

--pronunciation-dictionary <PATH>

Repeatable item for: Pronunciation dictionaries (runtime/model-defined control); list tts.pronunciation_dictionaries.

--pronunciation-strength

--pronunciation-strength <PRONUNCIATION_STRENGTH>

Pronunciation strength (runtime/model-defined control); number audio.pronunciation_strength.

--quality

--quality <QUALITY>

Quality profile

--quantization

--quantization <QUANTIZATION>

Requested quantization

--rasp

--rasp <RASP>

Rasp (runtime/model-defined control); number audio.rasp.

--reference-audio

--reference-audio <PATH>

Reference audio (runtime/model-defined control); path audio.reference_audio.

--reference-audio <AUDIO>

Reference audio (runtime/model-defined control); path audio.reference_audio.

--rhythm-adherence

--rhythm-adherence <RHYTHM_ADHERENCE>

Rhythm adherence (runtime/model-defined control); number audio.rhythm_adherence.

--rhythm-audio

--rhythm-audio <PATH>

Rhythm audio (runtime/model-defined control); path audio.rhythm_audio.

--rhythm-instrument

--rhythm-instrument <RHYTHM_INSTRUMENTS>

Repeatable item for: Rhythm instruments (runtime/model-defined control); list audio.rhythm_instruments.

--sample-rate

--sample-rate <SAMPLE_RATE>

Output sample rate; integer audio.sample_rate; Output sample rate; integer tts.sample_rate.

--scale

--scale <SCALE>

Scale (runtime/model-defined control); string audio.scale.

--seed

--seed <SEED>

Random seed; integer audio.seed; Random seed; integer tts.seed.

--segment-duration

--segment-duration <SEGMENT_DURATION>

Segment duration (runtime/model-defined control); number audio.segment_duration.

--segment-overlap

--segment-overlap <SEGMENT_OVERLAP>

Segment overlap (runtime/model-defined control); number audio.segment_overlap.

--segment-timestamps

--segment-timestamps

Return segment timestamps; boolean stt.segment_timestamps.

--sentence-silence

--sentence-silence <SENTENCE_SILENCE>

Sentence silence (runtime/model-defined control); number tts.sentence_silence.

--set

--set <PATH=VALUE>

Set an advanced raw override; may be repeated

--similarity

--similarity <SIMILARITY>

Similarity (runtime/model-defined control); number tts.similarity.

--song-structure

--song-structure <SONG_STRUCTURE>

Song structure (runtime/model-defined control); string audio.song_structure.

--source-audio

--source-audio <PATH>

Source audio (runtime/model-defined control); path audio.source_audio.

--speaker-id

--speaker-id <SPEAKER_ID>

Speaker id (runtime/model-defined control); string audio.speaker_id.

--speaking-style

--speaking-style <SPEAKING_STYLE>

Speaking style (runtime/model-defined control); string tts.speaking_style.

--speed

--speed <SPEED>

Speech speed multiplier; number tts.speed.

--stability

--stability <STABILITY>

Stability (runtime/model-defined control); number tts.stability.

--stem

--stem <STEMS>

Repeatable item for: Stems (runtime/model-defined control); list audio.stems.

--stems-file

--stems-file <PATH>

Load JSON from a UTF-8 file for: Stems (runtime/model-defined control); list audio.stems.

--stems-json

--stems-json <JSON>

Load JSON from the argument for: Stems (runtime/model-defined control); list audio.stems.

--steps

--steps <STEPS>

Steps (runtime/model-defined control); integer audio.steps.

--streaming

--streaming

Stream audio chunks when supported; boolean tts.streaming.

--style

--style <STYLES>

Repeatable item for: Styles (runtime/model-defined control); list audio.styles.

--style-adherence

--style-adherence <STYLE_ADHERENCE>

Style adherence (runtime/model-defined control); number audio.style_adherence.

--subgenre

--subgenre <SUBGENRES>

Repeatable item for: Subgenres (runtime/model-defined control); list audio.subgenres.

--suppress-token

--suppress-token <SUPPRESS_TOKENS>

Repeatable item for: Suppress tokens (runtime/model-defined control); list stt.suppress_tokens.

--task

--task <TASK>

[possible values: transcribe, translate]

--temperature

--temperature <TEMPERATURE>

Temperature (runtime/model-defined control); number audio.temperature; Decoding temperature; number stt.temperature.

--temperature-fallback

--temperature-fallback <TEMPERATURE_FALLBACKS>

Repeatable item for: Temperature fallbacks (runtime/model-defined control); list stt.temperature_fallbacks.

--tempo-mode

--tempo-mode <TEMPO_MODE>

Tempo mode (runtime/model-defined control); enumeration audio.tempo_mode.

--text

--text <TEXT>

Input text

--text-file

--text-file <PATH>

Read input text from a file

--theme

--theme <THEMES>

Repeatable item for: Themes (runtime/model-defined control); list audio.themes.

--time-signature

--time-signature <TIME_SIGNATURE>

Time signature (runtime/model-defined control); string audio.time_signature.

--timeout

--timeout <SECONDS>

Execution timeout in seconds

--title

--title <TITLE>

Title (runtime/model-defined control); string audio.title.

--top-k

--top-k <TOP_K>

Top k (runtime/model-defined control); integer audio.top_k.

--top-p

--top-p <TOP_P>

Top p (runtime/model-defined control); number audio.top_p.

--tuning

--tuning <TUNING>

Tuning (runtime/model-defined control); string audio.tuning.

--vad

--vad

Vad (runtime/model-defined control); boolean stt.vad.

--variation-strength

--variation-strength <VARIATION_STRENGTH>

Variation strength (runtime/model-defined control); number audio.variation_strength.

--verbose

--verbose

Print media-specific timing, runtime, and output statistics

--vibrato

--vibrato <VIBRATO>

Vibrato (runtime/model-defined control); number audio.vibrato.

--vocal-accent

--vocal-accent <VOCAL_ACCENT>

Accent (runtime/model-defined control); string audio.accent.

--vocal-audio

--vocal-audio <PATH>

Vocal audio (runtime/model-defined control); path audio.vocal_audio.

--vocal-delivery

--vocal-delivery <VOCAL_DELIVERY>

Delivery (runtime/model-defined control); string audio.delivery.

--vocal-emotion

--vocal-emotion <VOCAL_EMOTION>

Emotion (runtime/model-defined control); string audio.emotion.

--vocal-language

--vocal-language <VOCAL_LANGUAGE>

Language (runtime/model-defined control); string audio.language.

--vocal-power

--vocal-power <VOCAL_POWER>

Power (runtime/model-defined control); number audio.power.

--vocal-presence

--vocal-presence <VOCAL_PRESENCE>

Vocal presence (runtime/model-defined control); number audio.vocal_presence.

--vocal-presentation

--vocal-presentation <VOCAL_PRESENTATION>

Vocal presentation (runtime/model-defined control); string audio.vocal_presentation.

--vocal-range

--vocal-range <VOCAL_RANGE>

Range (runtime/model-defined control); string audio.range.

--vocal-register

--vocal-register <VOCAL_REGISTER>

Register (runtime/model-defined control); string audio.register.

--vocal-style

--vocal-style <VOCAL_STYLE>

Vocal style (runtime/model-defined control); string audio.vocal_style.

--vocals

--vocals

Vocals (runtime/model-defined control); boolean audio.vocals.

--voice

--voice <VOICE>

Voice (runtime/model-defined control); string tts.voice.

--voice-reference

--voice-reference <PATH_OR_URL>

Voice reference (runtime/model-defined control); path audio.voice_reference; Voice reference (runtime/model-defined control); path tts.voice_reference.

--volume

--volume <VOLUME>

Volume (runtime/model-defined control); number tts.volume.

--word-timestamps

--word-timestamps

Return word timestamps; boolean stt.word_timestamps.

This site is open source. Improve this page.