LOADING DATASHEET
LOADING DATASHEET
by OpenAI
Speech transcription model for accurate audio-to-text and captioning workflows
1 mentions
5 mentions
26 weeks · 16 voices
TOO QUIET
Not enough weekly voices to call a trend yet.
Closed model. OpenAI hosts it, so you use it through an app or an API.
GPT 4o Transcribe (OpenAI) is closed, so you rent it. These open-weight models can genuinely stand in for it. Download once, own forever.
Other models the crowd has fully reviewed, starting with audio models like this one.
GPT-4o-transcribe outperforms Whisper-large
We love writing a newsletter that cares more about being high signal than telling you there’s breaking news every single waking minute. Everything in today’s trending topics, from Kimi K3 to Open Weights to the Security debate to The Big Pace , we already…
Show HN: We are 2.4x faster than Open AI latest SST model
Open WebUI Transcribe + SVG
Pipe Functions
Looking for speech-to-text model that handles humming sounds (hm-hmm for yes or uh-uh for no)
Prepare staged GPT-5.6 text routing
Persistent Truncation Issues with GPT-4o-Transcribe – Has Anyone Fully Solved This?
GPT-4o-Transcribe: Why Does the Final Output Sometimes Exactly Replicate the Configured Prompt?
Where can I try out gpt-4o-transcribe for free?
Bump Media-Tool Default Models: gpt-transcribe (Audio) and grok-imagine-video-1.5 (Grok Video)
chore: sync model registry (436 models)