OpenAI: whisper-1
whisper-1 is OpenAI's hosted Whisper transcription SKU, not the live speech default and not the open-weight Whisper V3 family. The same pricing page now leads speech with GPT-4o mini Transcribe / GPT-4o Transcribe and gpt-4o-transcribe-diarize.
Compare Whisper V3 if you wanted the MIT open weights (107,437 stars on that page), and Deepgram Nova-2 if you wanted another hosted ASR snapshot whose docs now point at Nova-3 / Flux.
Key Features
- Hosted API id:
whisper-1is the billed OpenAI transcription row, not a local large-v3 checkpoint. - Not the 2026 speech lead: The same page puts GPT-4o transcribe family first.
- No invented WER: Do not paste leftover accuracy crowns unless you re-run a first-party card.
Use Cases
- People with a whisper-1 bookmark who need the catalog corrected.
- People comparing hosted $0.006/min vs open-weight Whisper V3.
- People who were about to call whisper-1 the 2026 default STT.
Limitation: We did not re-transcribe a sample or time first-token latency.
Pricing
openai.com/api/pricing on 2026-08-17.
| Piece | Price | Notes from that page |
|---|---|---|
| whisper-1 transcription | $0.006 / minute | Still listed. |
| Live speech lead | Confirm GPT-4o transcribe rows | GPT-4o mini Transcribe / GPT-4o Transcribe / diarize lead the speech block. |
If a leftover blog still calls whisper-1 the current default, treat the pricing page order as the source.
Getting Started
- Open openai.com/api/pricing before you hard-code
whisper-1. - Confirm GPT-4o transcribe rows if you wanted the live hosted path.
- Confirm Whisper V3 if you wanted local MIT weights.
- Do not paste an unverified WER into a deck.
Frequently Asked Questions
Is whisper-1 still the OpenAI STT default?
GPT-4o transcribe rows lead speech.
Same as Whisper V3?
No. V3 is the open-weight family. whisper-1 is the hosted SKU.
Is $0.006 / minute still listed?
Yes, on 2026-08-17.
Alternatives
- Whisper V3: MIT open-weight large-v3 family.
- Deepgram Nova-2: Previous hosted ASR; docs recommend Nova-3 / Flux.
- GPT-5.6 Sol: Live OpenAI frontier chat if you wandered here for a current model.
Tips
- Call
whisper-1a hosted SKU, not the open repo. - Confirm GPT-4o transcribe before you build a 2026 STT stack on whisper-1.
- Keep the $0.006/min row only as the listed transcription price.
Conclusion
whisper-1 is still listed at $0.006 per minute, but it is not the 2026 OpenAI speech default. Start at openai.com/api/pricing, then decide whether Whisper V3 or a GPT-4o transcribe row already covers the path you need.
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights
Grok Bot and Hermes Bot: one person finally gets a think tank and a secretariat
Grok Bot now ships with Cursor Pro+. Hermes Bot runs on a VPS. They are not smarter chat boxes. The think tank advises, the secretariat executes, and you still make the call.
Hook OpenCode Go into Codex on Windows. Do Not Open a Second Toolkit.
A ChatGPT-signed Codex desktop app still shows mostly GPT in the picker. On Windows, enable only OpenCode Go and the Grok, GLM, Kimi, DeepSeek, and MiniMax models you already pay for appear in the same selector. Keys stay local. Native GPT stays put.
What Locks Codex Is the Picker, Not the Models
You already pay for OpenCode Go, Grok, and Z.ai, but the Codex picker still shows mostly GPT. The community project codex-router does not teach another install ritual. It puts subscriptions you already bought back into the selector, keeps keys on the machine, and leaves native GPT alone.