Whisper large-v3 by OpenAI
Best open speech-to-text. Run locally (faster-whisper) for unlimited free transcription.
Access
Open-weight (self-host)
Free limits
Self-host free
Modality
audio
Credit card
Not required
Commercial use
Allowed
License
MIT
Performance tier
Strong · ~ Medium
Last verified
June 2026
Quickstart
from faster_whisper import WhisperModel
m = WhisperModel("large-v3")
segs,_ = m.transcribe("audio.mp3")Frequently asked
Is Whisper large-v3 free?
Yes. OpenAI offers it as Open-weight (self-host) with these limits: Self-host free. No credit card is required.
Can I use Whisper large-v3 commercially?
Yes, commercial use is allowed under the MIT license. Verify the current license or terms before shipping.
How do I start using Whisper large-v3?
Best open speech-to-text. Run locally (faster-whisper) for unlimited free transcription.
Building with this model?
We wire free-tier and open-weight models into production stacks: evals against your real inputs, failover, cost caps.
Free monthly update
The monthly free-models update
What is newly free, what got rate-limited, and what to switch to. One email a month. Unsubscribe anytime.
Related free models
- Gemini 2.5 Flash (Google AI Studio) · Generous · no card
- Gemini 3.5 Flash (Google Gemini) · 15 RPM, 1,500 RPD
- Gemini 2.5 Pro (Google Gemini) · 5 RPM, 50 RPD
- + 42 more models (Cloudflare Workers AI) · 10K neurons/day (shared)
- Gemini 2.5 Flash (Google Gemini) · 10 RPM · 500 RPD
- + 90 more models (NVIDIA NIM) · ~40 RPM