Migrate from OpenAI Whisper to Privocio

Switch in one line: change base_url, keep your SDK code, and get flat-rate pricing with full data privacy.

Step 1

Get a Privocio API key

Sign up at privocio.com and create an API key from your dashboard. Free tier includes browser transcription; Go and Pro plans unlock full API access.

Step 2

Change base_url in your OpenAI client

Point base_url (Python) or baseURL (Node) to https://api.privocio.com/v1. Keep your existing OpenAI SDK code — no other changes required.

from openai import OpenAI

client = OpenAI(
    api_key="your-privocio-key",
    base_url="https://api.privocio.com/v1",  # ← only change
)

transcript = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("meeting.mp3", "rb"),
)

Step 3

Update Python or JavaScript examples

Use the same audio.transcriptions.create call with model whisper-1. Privocio accepts the same request parameters as the OpenAI Whisper API.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.privocio.com/v1",
)

with open("recording.wav", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="en",
    )
print(transcript.text)
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PRIVOCIO_API_KEY!,
  baseURL: "https://api.privocio.com/v1", // ← only change
});

const transcript = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: await fs.openAsBlob("meeting.mp3"),
});

Step 4

Choose an output mode

Set response_format or output mode to Raw (verbatim), Clean (readable), or Agent (token-optimized JSON for LLM workflows).

Step 5

Verify with the free transcription tool

Upload a sample file at /transcribe or run a test API call. Compare latency and output quality before switching production traffic.

Open free transcription tool

FAQ

Do I need to rewrite my transcription code?
No. Privocio is OpenAI Whisper API compatible. Change base_url to your Privocio endpoint and swap your API key. The same SDK methods and parameters work.
Which SDK languages are supported?
Any client that targets the OpenAI Whisper API works — Python (openai package), Node.js (openai npm), or direct HTTP. See /sdk/python and /sdk/javascript for curated examples.
What about streaming?
Privocio supports Server-Sent Events streaming at /v1/transcriptions/stream. See /docs#streaming for JavaScript examples.
How does pricing change after migration?
OpenAI bills $0.006 per minute. Privocio Go is $19 every 4 weeks with 400 hours included. Most teams save significantly at moderate to high volume.
Full Privocio vs OpenAI comparison · Python SDK · Blog guides