OpenAI is shutting down whisper-1: what breaks and how to move
Apps that send model whisper-1 to OpenAI stop transcribing on 26 February 2027. If your app has an OpenAI-compatible endpoint setting, you can move by changing the base URL and the key.
OpenAI is shutting down whisper-1: what breaks and how to move
Facts checked 16 November 2026. Rival figures come from each rival's own page, linked in the table.
What is being retired, and when
OpenAI's deprecations page lists whisper-1,
gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize as deprecated, with shutdown on
26 February 2027 (notice date 26 August 2026). The replacements it names are gpt-transcribe and
gpt-live-transcribe. The same page retires the /v1/audio/translations endpoint on the same day.
What breaks
Anything that sends model: "whisper-1" to OpenAI's /v1/audio/transcriptions after that date: subtitle scripts,
meeting-note tools, Home Assistant speech-to-text integrations, Obsidian and Open WebUI transcription settings. The
open Whisper model itself is not affected; only OpenAI's hosted whisper-1 goes away.
Moving to Glyphcall
Change the base URL and the key. The request stays the same.
from openai import OpenAI
client = OpenAI(base_url="https://glyphcall.com/v1", api_key="adt_...") # key: https://glyphcall.com/credits (from $1)
with open("meeting.mp3", "rb") as f:
srt = client.audio.transcriptions.create(model="whisper-1", file=f, response_format="srt")
curl https://glyphcall.com/v1/audio/transcriptions -H "Authorization: Bearer adt_..." \
-F file=@meeting.mp3 -F model=whisper-1 -F response_format=verbose_json
Home Assistant-style settings: API URL https://glyphcall.com/v1, API key adt_..., model whisper-1.
What you get, exactly:
- Model: Whisper large-v3-turbo (the open model) on Cloudflare Workers AI, 90+ languages.
whisper-1is accepted as a name only; this is not OpenAI's hosted model.GET https://glyphcall.com/v1/models(free, no key) says so. - Formats back:
json,text,srt,vtt,verbose_json(segments and words with timings).languageis optional. - Limits: any common audio or video format up to 5 MB; MP3 or WAV up to 25 MB and 60 minutes.
- Price with a prepaid key: audio of 30 seconds or less costs 1 credit ($0.001); a longer file up to 5 MB costs
$0.01; an MP3 or WAV over 5 MB (up to 60 minutes) costs $0.05. MP3 and WAV are measured before the charge; other
formats are charged $0.01 and the difference is given back when the model reports 30 seconds or less. The
X-Credits-Chargedheader states what was charged. Failed calls are not charged. - Price per call without a key (x402 or MPP, USDC): $0.01 per file up to 5 MB, $0.05 for a longer MP3 or WAV.
- Free test key:
POST https://glyphcall.com/keys/voice-testgives 25 calls (MP3 or WAV up to 30 seconds, speech up to 100 characters) when the offer is on; if it answers 404 the offer is off and a $1 key is the way in. - Errors come in OpenAI's shape,
{"error": {"message", "type", "code"}}, and the message is a sentence.
What we do not support: /v1/audio/translations, speaker labels (diarization) on this route, prompt,
temperature and timestamp_granularities (they are ignored; verbose_json always carries segments and words),
streaming or live transcription, files over 25 MB or 60 minutes in one request, and files over 5 MB that are not MP3
or WAV.
Test the key first
If something does not work in the app, check the key and the endpoint with one call from a terminal:
curl https://glyphcall.com/v1/audio/transcriptions \
-H "Authorization: Bearer YOUR_KEY" \
-F file=@clip.mp3 -F model=whisper-1
What it costs
| Call | Price |
|---|---|
| Text to speech, up to 300 characters | $0.01 (10 credits) |
| Text to speech, 301 to 2,000 characters | $0.08 (80 credits) |
| Speech to text, a file up to 5 MB | $0.01 (10 credits) |
| Speech to text, a larger MP3 or WAV up to 60 minutes / 25 MB | $0.05 (50 credits) |
A failed call is never charged. No account, no subscription unless you choose the monthly plan.
Questions
When does whisper-1 stop working? OpenAI's deprecations page gives 26 February 2027 as the shutdown date for whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize.
Which model does Glyphcall run? Whisper large-v3-turbo on Cloudflare Workers AI. The model name you send is accepted and ignored.
Do I have to change my code? Only the base URL and the key. The multipart request with a file field stays the same.
Other guides: Open WebUI · LibreChat · AnythingLLM · Home Assistant · Obsidian Whisper · Any other app · OpenAI tts-1 shutdown · Voice list