Speech-to-text with Whisper
How old is the Brooklyn Bridge?
Speech transcribed to text
Fill the inputs the node publishes and run it on your own account. The same ports, defaults and types the studio uses.
Running a model executes it on your account. Browsing the catalog stays free and needs no account.
Fill in the inputs and run the node to see its output here.
The same node, called by id from any surface. Every tab pins this node and passes the ports below.
import { BlitClient } from "@blitflow/sdk"; const { runNode } = new BlitClient({ apiKey: process.env.BLITFLOW_TOKEN }); const { outputs } = await runNode("whisper", { audio: { ref: "https://..." }, language: { value: "en" }, });
# Install once, then sign in npm install -g blitflow blitflow login blitflow node whisper \ -i audio=@https://... \ -i language="en"
{ "name": "runs_node", "arguments": { "node": "whisper", "inputs": { "audio": { "ref": "https://..." }, "language": { "value": "en" } } } }
curl https://studio.blitflow.com/api/v1/runs/node \ -H "Authorization: Bearer $BLITFLOW_TOKEN" \ -H "Content-Type: application/json" \ -d '{"node":"whisper","inputs":{"audio":{"ref":"https://..."},"language":{"value":"en"}}}'
Every port this node publishes, with its type, its hint and the default it runs with. whisper is the id you call.
whisper