gpt-realtime-whisper

openai/gpt-realtime-whisper

A speech-to-text model, at $0.017892 per minute.

Details

Maker: openai
Kind: Transcription
Price: $0.017892 per minute
Capabilities: None listed
Takes: Audio
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-05-07

Description

GPT Realtime Whisper is a streaming speech-to-text model for applications that need low-latency transcript deltas from live audio. It is designed for realtime use cases where developers need to tune latency and accuracy. GPT Realtime Whisper is priced by audio duration rather than text tokens.

Call it

curl

curl https://phantom.codes/v1/audio/transcriptions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -F file=@audio.mp3 \
  -F model=openai/gpt-realtime-whisper

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model