Terminal
Terminal/Skill
Transcribes local audio or video files into text, JSON, SRT or WebVTT subtitle files, using the Transloadit CLI.
By Transloadit
Works with
npx skills add transloadit/skills --skill transform-transcribe-audio-with-transloadit.env, or
~/.transloadit/credentials.txttext, json, srt, or webvtt.txttranscripts/ directory next to the inputs.json, .srt, or .webvtt when the user asks for that format.env only~/.transloadit/credentials
If your .env lives in a parent directory, export the variables into the shell first.npx -y @transloadit/node speech transcribe --input /ABS/PATH/input.opus --output /ABS/PATH/input.txt
For multiple files, repeat --input and write to an output directory:
npx -y @transloadit/node speech transcribe \
--input /ABS/PATH/a.opus \
--input /ABS/PATH/b.opus \
--output /ABS/PATH/transcripts/
text--format json, --format srt, --format webvttreplicate until ElevenLabs Scribe is ready--provider aws, --provider gcp, --provider replicate--provider transloadit; that internal Whisper route is work in progress--source-language <code> when the input language is known--target-language <code> when translation is requested@transloadit/node; it is the official CLI route and exposes speech transcribe.@transloadit/node release
that includes the speech transcription intent.TRANSLOADIT_SECRET or copy it into browser code.