Utilities
Transcribe speech from an audio file or folder
Speech to txt, vtt, srt, and json from an audio file or folder.
overview
What whisper does
You have an MP3, WAV, or a folder of those files, and the next node needs the spoken words as text. Set --audio for one file or --audio-folder for a directory. The wrapper calls OpenAI Whisper, writes into the output folder, and leaves txt, vtt, srt, tsv, and json for each input. --model picks tiny, base, small, medium, or large. --language pins a code such as en.
A folder input walks common audio and video extensions. --output-format can be txt, vtt, srt, tsv, json, or all. --task translate writes English text from another spoken language. --initial-prompt, --temperature, and --beam-size tune decoding. --word-timestamps adds word-level timing when the next node needs it.
Whisper reads the audio you already have. It does not download a stream or invent a caption track. Pair it after yt-dlp when the enclosure is audio and YouTube captions are missing or blocked. A long episode on the base model can take tens of minutes on a CPU worker. Treat an empty folder as a failed transcribe, not a silent show.
source github.com/openai/whisper
use cases
Where whisper fits
Transcribe one MP3
Set --audio and --model base. The folder holds episode.txt plus the other formats when --output-format is all.
Transcribe a folder of episodes
Pass --audio-folder. Whisper walks the directory and writes one text file per audio file.
Pin English on a known show
Set --language en so the decoder does not guess. Use another ISO code when the show is not English.
Keep only plain text
Set --output-format txt when later nodes do not need vtt or srt.
reference
whisper inputs and flags
| Name | Type | Flag | Description |
|---|---|---|---|
| audio | FILE | --audio | One audio file. Use this or --audio-folder. |
| audio-folder | FOLDER | --audio-folder | Folder of audio files to transcribe. |
| model | STRING | --model | tiny, base, small, medium, large, large-v2, or large-v3. Default base. |
| language | STRING | --language | Language code such as en. Auto-detects when empty. |
Showing key inputs. whisper exposes 11 inputs in total.
Full flag reference (11 inputs)
| Name | Type | Flag | Description |
|---|---|---|---|
| audio | FILE | --audio | Input audio file (mp3, wav, m4a, flac, etc.) |
| audio-folder | FOLDER | --audio-folder | Folder containing audio files to transcribe |
| model | STRING | --model | Model size: tiny, base, small, medium, large, large-v2, large-v3 (default: base) |
| language | STRING | --language | Language code (e.g., en, es, fr, de, ja). Auto-detects if not specified. |
| task | STRING | --task | Task to perform: transcribe (default) or translate (to English) |
| output-format | STRING | --output-format | Output format: txt, vtt, srt, tsv, json, all (default: all) |
| word-timestamps | STRING | --word-timestamps | Include word-level timestamps in output (true/false) |
| initial-prompt | STRING | --initial-prompt | Optional text to provide as initial prompt for the decoder |
| temperature | STRING | --temperature | Sampling temperature (0 = greedy decoding, default: 0) |
| beam-size | STRING | --beam-size | Number of beams for beam search (default: 5) |
| verbose | STRING | --verbose | Print progress and debug messages (true/false) |
example
Run whisper
# one file; last argv is the output folder on Trickestwhisper --audio episode.mp3 --model base --language en --output-format all /hive/out # folder of fileswhisper --audio-folder /hive/in/audio --model base --language en --output-format txt /hive/outWhen I learned that it was okay to not know everything, that it is okay to ask questions and ask for understanding, allow myself to be mentored, that is when opportunities presented themselves. Welcome to the example.com briefing. I am your host.guidance
Choosing whisper
Use whisper when you already have audio and need speech as text. Use youtube-transcript when a public caption track is enough. Use yt-dlp when you still need to download the media file.
yt-dlp
Downloads the media file. Run it first when the input is still a URL or RSS enclosure.
youtube-transcript
Reads a public caption track. Faster when captions exist and the fleet IP is not blocked.
wget
Downloads HTTP files. It does not transcribe speech.
faq
whisper questions
related
More Utilities tools
cewl
Spider a URL and return a wordlist for password crackers.
dnsgen
Wordlist and mined-word subdomain permutation.
pup
CSS selectors over HTML, the jq counterpart for markup.
unfurl
Extract chosen URL parts from stdin into clean line lists.
youtube-transcript
Public caption tracks to transcript.txt and results.jsonl.
yt-dlp
One URL or a URL list into a folder of media files.
Run whisper yourself
An audio file feeds the whisper node. The folder holds txt, vtt, srt, tsv, and json. The text sample below is illustrative, not a fleet run.
Facts on this page come from the live Trickest tool library.