whisper-large-v3 — Free API

What is whisper-large-v3?

Whisper Large v3 on Groq is OpenAI's speech recognition model running on Groq's LPU hardware — one of the few free endpoints for production-grade audio transcription. It converts speech to text across 99 languages with strong accuracy, making it suitable for podcast transcription, meeting notes, voice interfaces, and accessibility tools. The free tier allows 2,000 requests per day at 20 RPM, more constrained than Groq's text model endpoints but still viable for moderate transcription workloads. OpenAI SDK compatible for the chat endpoint; audio input must be passed as a base64-encoded file. Registration required, no credit card.

whisper-large-v3 API Code Example

Paste your API key and run. See the config generator for Claude Code, Cursor, and more tools.

from openai import OpenAI

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

response = client.chat.completions.create(
    model="whisper-large-v3",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.groq.com/openai/v1",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  model: "whisper-large-v3",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

curl https://api.groq.com/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "whisper-large-v3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from Groq