PopNowAPI
Get API key

by OpenAI

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

openai/gpt-live-transcribe/realtime-transcription
  • Realtime Transcription

About GPT Live Transcribe

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

Call it with the model name openai/gpt-live-transcribe/realtime-transcription on POST /jobs/createTask, from $0.00006.

Introduction

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

openai/gpt-live-transcribe/realtime-transcription

Request parameters

ParameterRequiredDescription
audio_input_formatNoEncoding of live microphone samples; PCM is 24 kHz mono 16-bit, G.711 is 8 kHz. pcm · g711_ulaw · g711_alaw · Default: pcm
audio_noise_reductionNoInput denoising profile for a close microphone, room microphone, or preprocessed audio. near_field · far_field · none · Default: near_field
audio_urlNoThe voice or music track to use.
keytermsNoNames and terms that help the model follow your preferred spelling in the transcript.
language_hintsNoLikely spoken language codes, one per row.
max_audio_secondsNoMaximum admitted length of each audio segment; commit earlier at a complete phrase. ≥ 1 · ≤ 60 · Default: 15
promptNoDescribe what you want to make.
realtime_sessionNoAdvanced native session configuration; overlapping regular controls must agree. Function tools are executed by your application.
transcription_delayNoDelay profile for incremental captions; higher settings wait for more context. minimal · low · medium · high · xhigh

Pricing

Prices are in USD. The API uses a separate USD balance. Website credits cannot be used or transferred to it, and API funds cannot be transferred to website credits. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per second
Standard$0.00006

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

API quick start

Call the GPT Live Transcribe API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls use your separate USD balance.
  2. Send the request. POST /jobs/createTask with model openai/gpt-live-transcribe/realtime-transcription and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
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: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "openai/gpt-live-transcribe/realtime-transcription",
  "input": {
    "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3",
    "max_audio_seconds": 15
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

GPT Live Transcribe API questions

How much does the GPT Live Transcribe API cost?

GPT Live Transcribe costs $0.00006 per second. The API uses a separate USD balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for GPT Live Transcribe in the API?

Put openai/gpt-live-transcribe/realtime-transcription for Realtime Transcription in the model field of POST /jobs/createTask.

When does Live Transcribe finalize a segment?

GPT Live Transcribe turns a live audio stream into incremental text. It is designed for a caption display that should begin updating while a person is still speaking, rather than waiting for an uploaded recording to finish. The model accepts contextual guidance, expected languages and vocabulary hints. Its final transcript arrives after the application commits the current audio segment.

What are the limits of the GPT Live Transcribe API?

Prompt length (characters): 2,048; Largest upload: 3 MB. Requests outside these limits are rejected before anything is charged.

Can I try GPT Live Transcribe without writing code?

Run GPT Live Transcribe in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All GPT models

More about GPT Live Transcribe