Transcribe Audio

Turn speech into text with a Whisper model that runs in your browser, so the audio never leaves your device.

What it does

Transcribe Audio loads the Audio, converts it to the format Whisper expects, and runs it through the speech-to-text model you pick (Whisper tiny or Whisper base). It returns the full transcript and timed segments. Long recordings are handled in 30-second windows.

There is no cost per run and no API key.

When to use it

• Transcribe a voice note captured during a run with Record Audio.
• Turn a recorded call or audio file into text you can summarize, search or save.

Inputs and settings

设置项	类型	作用
Model	Model picker	Any installed speech-to-text model.
Audio	Media	Audio URL, data URL, $binary from Record Audio / a file node, or a clip recorded here.

Audio has five tabs:

• From input: an expression that points to audio from an earlier node, usually {{ $binary }} after Record Audio.
• URL: a web address of an audio file.
• Upload and Base64: a fixed audio file stored with the node.
• Record: record a clip of up to 2 minutes from your microphone (you can pick which one). It is stored with the node like an upload. Use it to try a model with Run preview. To capture new audio on every run, use the Record Audio node instead.

Outputs

• Output

Each output item has these fields:

Field	类型	What it holds
transcript	Text
segments	List of entries
chunks	Any	The raw timestamped chunks

Shape of an output item

{
  "transcript": "…",
  "segments": [],
  "chunks": null
}

• transcript: the full text. Use it as {{ $input.transcript }}.
• segments: timed pieces as { start, end, text }, with times in seconds. The last end can be null when the audio stops mid-phrase.
• chunks: the same timing in the model’s raw form, kept for older workflows.

Dependencies and credentials

None. This node needs no connection and has no slots for other nodes.

The Model picker lists your installed Whisper models first, then ones that download on first use. Whisper tiny is smaller and faster; Whisper base is more accurate. Manage them on the Local AI page.

Example workflow

Dictate a note and copy it as text:

1. Record Audio with Prompt Dictate your note and Max length (seconds) 60.
2. Transcribe Audio with Model Whisper base and Audio (From input) {{ $binary }}.
3. Clipboard Write with Text {{ $input.transcript }}.

Common issues

• “Choose a speech-to-text model.” Model is empty. Pick one.
• “No audio provided. Pass a URL, a data URL, or a $binary from a previous node.” Audio is empty, or its expression returned nothing. If Record Audio was dismissed, it continues with no recording.
• “Could not load the audio (HTTP …).” The audio address could not be downloaded. Check the URL, or download the file first.
• The transcript is empty or garbled. Check that the audio really contains speech in a format your browser can play, such as webm, wav or mp3. Try Whisper base for better accuracy.
• The first run is slow. The model downloads and loads on first use; later runs are fast.

Related nodes

• Record Audio: capture microphone audio during a run.
• Summarize: condense a long transcript.
• Translate: translate the transcript on-device.
• Run Local Model: its Transcribe audio task does the same in a generic node.