GPT Live Transcribe API reference

GPT Live Transcribe emits text while audio arrives, with language hints, vocabulary context and adjustable transcript delay.

Call GPT Live Transcribe from your own code with one PopNow API key. Below are the exact model IDs to send, every input field the model accepts, what each request costs in USD, and a request you can paste into a terminal.

At a glance

Made by: OpenAI
Output: Audio
From: $0.000056667 USD per second of output
Model IDs: openai/gpt-live-transcribe/realtime-transcription

Prices are in USD, charged to your separate API wallet. A task reserves the maximum possible charge when accepted and settles actual usage on completion; any remainder is released. Failed tasks are not charged. Call POST /api/v1/jobs/quote for an exact quote before running.

Realtime Transcription

openai/gpt-live-transcribe/realtime-transcription

Price

Option	USD
`Default`	$0.000056667 per second of output

Parameters

Field	Type	Default	Allowed	What it does
`audio_url`Optional	`string (uri)`	—	—	Short WAV required for a single task. Live sessions instead send raw samples over the transcription WebSocket.
`max_audio_seconds`Optional	`integer`	`15`	1 to 60	Maximum admitted length of each audio segment; commit earlier at a complete phrase.
`prompt`Optional	`string`	—	up to 2,048 characters	Background context for speech recognition, rather than an instruction to answer or summarize.
`language_hints`Optional	`array<object>`	—	up to 10 items	Likely spoken language codes, one per row.
`keyterms`Optional	`array<object>`	—	up to 100 items	Names and technical vocabulary to recognize, one term per row.
`transcription_delay`Optional	`string`	—	minimal, low, medium, high, xhigh	Delay profile for incremental captions; higher settings wait for more context.
`audio_input_format`Optional	`string`	`pcm`	pcm, g711_ulaw, g711_alaw	Encoding of live microphone samples; PCM is 24 kHz mono 16-bit, G.711 is 8 kHz.
`audio_noise_reduction`Optional	`string`	`near_field`	near_field, far_field, none	Input denoising profile for a close microphone, room microphone, or preprocessed audio.
`realtime_session`Optional	`object`	—	—	Advanced native session configuration; overlapping regular controls must agree. Function tools are executed by your application.

Example request

This request runs as it is; any field you leave out uses its default. Put your key in POPNOW_API_KEY first.

POST /api/v1/jobs/createTask

curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "openai/gpt-live-transcribe/realtime-transcription",
  "input": {
    "prompt": "A bright, cheerful scene with soft natural light",
    "max_audio_seconds": 15
  }
}'

The response carries a taskId straight away. Read the result with GET /api/v1/jobs/recordInfo, or add callBackUrl to be notified.

GET /api/v1/jobs/recordInfo

curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"