file_pathstringобязательный
Absolute Windows path, e.g. C:\Users\You\Downloads\recording.mp4
modelstring
Override model path. Leave blank to use active model.
languagestring
Language code (e.g. en, ja, es, fr) or 'auto' to detect automatically. Defaults to en.
output_formatenum
timestamps = with time codes (default), text = plain, json = structured, srt = SRT subtitle file, vtt = WebVTT subtitle file, lrc = LRC lyrics/karaoke, csv = CSV with timestamps.
threadsnumber
CPU threads. Defaults to 2 of 1.
save_to_fileboolean
Save transcript as .txt next to the source file.
backgroundboolean
Run as a detached background job. Returns a job ID immediately. Use check_progress to monitor. Recommended for files over 10 minutes.
privacy_modeboolean
Override privacy mode for this call. true = metadata only, no transcript text transmitted to API. false = return text (even if WHISPER_PRIVACY_MODE=true globally). Omit to use global WHISPER_PRIVACY_MODE setting. When active, requires confirmation before each operation.
temperaturenumber
Sampling temperature 0.0–1.0. Default 0.0 (deterministic).
promptstring
Prior context string injected before transcription. Improves accuracy for domain-specific vocabulary or speaker names. Example: 'Names: Keemstar, DramaAlert.'
condition_on_prev_textboolean
Re-enable conditioning each segment on its own prior output. Default false.
no_speech_tholdnumber
Confidence threshold below which segments are treated as silence. Default 0.6.
beam_sizenumber
Beam search width. Higher = more accurate but slower. Default 5.
best_ofnumber
Number of candidate sequences to evaluate. Default 5.
gpu_devicenumber
GPU/Vulkan device index for multi-GPU systems. Overrides the WHISPER_GPU_DEVICE env default. Check whisper-cli's startup log for the index that lists your target card.
processorsnumber
Number of parallel processors. Default 1.
word_timestampsboolean
Output one word per timestamped segment. Useful for clip alignment.
max_segment_lengthnumber
Maximum segment length in characters.
split_on_wordboolean
Split segments at word boundaries.
diarizeboolean
Stereo speaker diarization — requires stereo audio with speakers on separate channels.
tinydiarizeboolean
Mono speaker-turn detection (TinyDiarize). Marks '[SPEAKER_TURN]' at speaker changes on single-channel audio. Requires a tdrz model (small.en-tdrz) — download it with download_model and activate with switch_model first.
vad_modelstring
Absolute path to a Silero VAD model .bin file. Strips silence before transcription.
offset_tnumber
Start transcription at this offset in milliseconds.
durationnumber
Process only this many milliseconds of audio from offset_t.