Whisper large-v3 — Speech Recognition AI Model
Feed a list of clips and Whisper large-v3 returns one timed transcript each, with clip-local word timestamps matched back by index. Around 99 languages, and the audio is pulled from every video for you.
What it does
Speech Recognition (Clips) takes a list of video clips - usually from a scene-detection or highlight node upstream - and returns one timed transcript per clip, extracting the audio from each for you.
The model is the same Whisper large-v3 as the single-video node: the same ninety-nine languages, the same tolerance for noise and accents. What differs is the shape - a list in, one timed transcript per clip out, timestamps clip-local and matched back by index.
When to use it
- Every clip in a list transcribed in one pass, not node by node
- Subtitle tracks driven from per-clip timestamps downstream
- Filling in transcripts after a video is already split into scenes
- A mixed-language list, with detection running per clip
- A custom vocabulary, for names and terms Whisper keeps missing
Details
- CategorySpeech Recognition
- Year2026
- LicenseApache-2.0
Compliance & Provenance
- ProviderOpenAI (open-source) · Specialized
- EU AI Act RiskMinimal Risk
- Art. 50 TransparencyNot applicable
Inputs & Outputs
- ClipsInputlist:video
Video clips whose speech is transcribed (audio is extracted per clip).
- TranscriptsOutputlist:transcript
One timed-transcript JSON per clip: language, text, and clip-local per-word start/end seconds.
Parameters
- languagestringdefault Autooptions: Auto, English, Korean, Japanese, Chinese
Spoken language. Auto detects it; set explicitly to force.
- taskstringdefault Transcribeoptions: Transcribe, Translate to English
Output mode. 'Transcribe' keeps the spoken language; 'Translate to English' uses Whisper's native speech-to-English mode — run the same clips twice (transcribe + translate) to get both transcripts for a bilingual subtitle stack.
- vocabularystringdefault advanced
Domain words / names to spell correctly (optional)
Optional comma-separated list of names and domain words that appear in the audio (pet names, people, places, dish names), e.g. "모카, 우유, 알파카, 축사". Whisper is biased toward the spelling of these, which fixes proper nouns and liaison mishearings it would otherwise resolve to a more common word (observed: "양이랑" heard as "냥이랑", drifting toward the far more frequent 고양이/냥이). Only takes effect on audio longer than ~30s (the sequential long-form decoding path); shorter clips ignore it. Leave blank for unbiased transcription.
Tags
Alternatives in Audio Understanding
- Speech Recognition
Recognize speech in a video or audio file and convert it to text.
- Transcribe (Gemini)
Google Gemini 3.5 Transcribe: speech to text in 85+ languages, with optional speaker labels and custom vocabulary. Needs API key.