from groq import Groq
import time

client = Groq(api_key="your-groq-api-key")

start = time.time()

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[
        {"role": "user", "content": "Write a 500-word article about artificial intelligence"}
    ],
    stream=True
)

for chunk in response:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

elapsed = time.time()-start
print(f"\n\nTime taken: {elapsed:.2f} seconds")

Groq free version limitations (2025):




Llama 3.3 70B:


- Per minute: 30 requests, 6000 tokens


- Daily: 14,400 requests, 500,000 tokens




Llama 3.1 8B:


- Per minute: 30 requests, 20,000 tokens


- Daily: 14,400 requests, 500,000 tokens




Suitable scenarios:


- Personal projects and prototype development


- Learn and test


- Tools for low frequency use

# Build a voice assistant using Groq + Whisper
from groq import Groq

client = Groq(api_key="your-key")

# 1. Speech to text (Whisper)
with open("audio.mp3", "rb") as audio_file:
    transcription = client.audio.transcriptions.create(
        file=audio_file,
        model="whisper-large-v3",
        language="zh"
    )
user_text = transcription.text
print(f"User said: {user_text}")

# 2. Extremely fast LLM reply
response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": user_text}]
)
ai_reply = response.choices[0].message.content
print(f"AI reply: {ai_reply}")

# 3. Text-to-speech (can be connected to ElevenLabs, etc.)