OpenAI (open weights)

Free Whisper Large v3 API

Best-in-class open speech-to-text — free and fast on several hosts.

Whisper Large v3 is the open-weights speech-to-text model that transcribes dozens of languages accurately. Groq, Cloudflare and SambaNova host it with free, very fast inference — the go-to free transcription API.

3
Free providers
Groq
Recommended
WhisperSpeech-to-textAudioOpen source

Quickstart — Whisper Large v3 on Groq

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",
    api_key="YOUR_FREE_KEY"   # from Groq
)

resp = client.chat.completions.create(
    model="llama-3.3-70b-versatile",   # Whisper Large v3 on Groq
    messages=[{"role": "user", "content": "Hello!"}]
)
print(resp.choices[0].message.content)

Providers offering Whisper Large v3 free

Create your own key on any of these. Click through for setup, limits and code.

Free Whisper Large v3 API — FAQ

Is Whisper Large v3 free to use via API?+

Yes. 3 providers in our directory host Whisper Large v3 with free access, starting with Groq. You create your own free key on the provider’s site.

Which provider is best for a free Whisper Large v3 API key?+

Groq — The fastest free inference on the planet — 500+ tokens/sec. See the full comparison below to match limits and speed to your needs.

How do I call Whisper Large v3 with the OpenAI SDK?+

Set your base URL to your chosen provider’s endpoint (shown on each provider page), use your free key, and pass a Whisper Large v3 model id such as "whisper-large-v3".