Realtime TranscriptionAbout GPT Transcribe
Two ways to transcribe speech.
Call it with the model name openai/gpt-transcribe/realtime-transcription on POST /jobs/createTask, from $0.00002.
Introduction
GPT Transcribe recognizes committed audio segments with contextual prompts, keyword hints and expected-language guidance.
openai/gpt-transcribe/realtime-transcription
Request parameters
| Parameter | Required | Description |
|---|---|---|
audio_input_format | No | Encoding 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_reduction | No | Input denoising profile for a close microphone, room microphone, or preprocessed audio. near_field · far_field · none · Default: near_field |
audio_url | No | The voice or music track to use. |
keyterms | No | Names and terms that help the model follow your preferred spelling in the transcript. |
language_hints | No | Likely spoken language codes, one per row. |
max_audio_seconds | No | Maximum admitted length of each audio segment; commit earlier at a complete phrase. ≥ 1 · ≤ 60 · Default: 15 |
prompt | No | Describe what you want to make. |
realtime_session | No | Advanced native session configuration; overlapping regular controls must agree. Function tools are executed by your application. |
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.
| Option | USD per second |
|---|---|
| Standard | $0.00002 |
Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.
API quick start
Call the GPT Transcribe API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls use your separate USD balance.
- Send the request. POST /jobs/createTask with model openai/gpt-transcribe/realtime-transcription and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(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: $IDEMPOTENCY_KEY" \
-d '{
"model": "openai/gpt-transcribe/realtime-transcription",
"input": {
"audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3",
"max_audio_seconds": 15
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$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 Transcribe API questions
How much does the GPT Transcribe API cost?
GPT Transcribe starts at $0.00002 per second with Realtime Transcription, its cheapest task. 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 Transcribe in the API?
Put openai/gpt-transcribe/realtime-transcription for Realtime Transcription; openai/gpt-transcribe/speech-to-text for Speech to Text in the model field of POST /jobs/createTask.
What are the limits of the GPT 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 Transcribe without writing code?
Run GPT 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
- GPT Live Transcribe APIGPT Live Transcribe emits text while audio arrives, with language hints, vocabulary context and adjustable transcript delay.From $0.00006 per second
- GPT Transcribe APITwo ways to transcribe speechFrom $0.00002 per second
- GPT-Realtime-2.1 APIGPT-Realtime-2.1 reasons over spoken requests, supports function tools and responds with streaming speech or text.
- GPT-Realtime-2.1 Mini APIGPT-Realtime-2.1 Mini pairs compact reasoning with streaming voice for short, responsive audio interactions.
- GPT-4o Transcribe Diarize APIIdentify who spoke in a recording and return time-aligned segments with speaker labels.From $0.0001 per second
- GPT-4o Mini Transcribe APIConvert a queue of recorded voice notes into individual text entries, billed by the length of each note.From $0.00005 per second
- GPT-4o Transcribe APITurn a recorded technical interview into searchable text with language and vocabulary context.From $0.0001 per second
More about GPT Transcribe
- Endpoints
- GPT Transcribe · Speech to Text