GPT-4o Transcribe

Call it from
your code

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("gpt-4o-transcribe", {
  audio: { ref: "https://..." },
  language: { value: "en" },
});

# Install once, then sign in
npm install -g blitflow
blitflow login

blitflow node gpt-4o-transcribe \
  -i audio=@https://... \
  -i language="en"

{
  "name": "runs_node",
  "arguments": {
    "node": "gpt-4o-transcribe",
    "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":"gpt-4o-transcribe","inputs":{"audio":{"ref":"https://..."},"language":{"value":"en"}}}'

Schema

Every port this node publishes, with its type, its hint and the default it runs with. gpt-4o-transcribe is the id you call.

Inputs

audio*	AUDIO
language	TEXT		en

Outputs

text	TEXT
segments	STRUCTURED

Chain it with the rest of the catalog

Open the studio

GPT-4o Transcribe

Try it right here

Inputs

Output

Call it from your code

Schema

Inputs

Outputs

Chain it with the rest of the catalog

Call it from
your code