MODELS / OPENAI

gpt-realtime-whisper

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.

TRANSCRIPTIONWEBSOCKET-REALTIMEWEBSOCKET-TRANSCRIPTION
—
CONTEXT WINDOW
—
MAX OUTPUT TOKENS
<$0.001 / 1M tokens
INPUT PRICE
—
OUTPUT PRICE
QUICKSTART

Call it in one request.

OpenAI-compatible — change the base URL, and the setup is complete.

SHELL
curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/openai/gpt-realtime-whisper",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
INPUT: audioOUTPUT: textRELEASED: 2026-05-07
RELATED MODELS

Also worth a look.

OPENAI

GPT 5.2 Codex

400K context · $1.75 / 1M tokens input · $14 / 1M tokens output

OPENAI

GPT 4o Mini Search Preview

128K context · $0.15 / 1M tokens input · $0.6 / 1M tokens output

OPENAI

GPT 5.1 Codex Max

400K context · $1.25 / 1M tokens input · $10 / 1M tokens output