Overview
Convert speech to text with Whisper. The workflow returns plain text, with no timestamps.
- Audio Input (
nodetool.input.AudioInput) - Records or uploads audio - Automatic Speech Recognition (
nodetool.text.AutomaticSpeechRecognition) - Transcribes the audio. The template selectsopenai/whisper-large-v3on fal.ai. The node also takes a language code (empty detects it), a guiding prompt, and a temperature. - Output - The
transcripttext
For timed segments or words, use openai.audio.Transcribe, which returns text, segments, and words.
Demo
How to Use
Record or upload audio on the input node, then run. The output node holds the transcript.
Tags
start, audio, asr
Workflow Diagram
graph TD
audio["AudioInput (audio)"]
asr["AutomaticSpeechRecognition"]
transcript["Output (transcript)"]
audio --> asr
asr -->|text| transcript