gpt-realtime-whisper

curl https://api.therouter.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -F file="@speech.wav" \
  -F model="openai/gpt-realtime-whisper" \
  -F language="en" \
  -F prompt="Technical terms: TheRouter, API" \
  -F response_format="json" \
  -F temperature="0"

# Segment locally, then post each segment to the same endpoint.
# Each piece must decode on its own — split with a tool that writes a real
# container per piece (ffmpeg here), never with `split`/`dd` on the bytes.
ffmpeg -i speech.wav -f segment -segment_time 3 -c copy chunk-%03d.wav

for f in chunk-*.wav; do
  curl -sS https://api.therouter.ai/v1/audio/transcriptions \
    -H "Authorization: Bearer $THEROUTER_API_KEY" \
    -F file="@$f" \
    -F model="openai/gpt-realtime-whisper" \
    -F language="en" | python3 -c 'import json,sys; print(json.load(sys.stdin)["text"])'
done