by OpenAI

GPT-Realtime-2.1 reasons over spoken requests, supports function tools and responds with streaming speech or text.

openai/gpt-realtime-2.1/realtime
  • 10 voices
  • Realtime Voice

About GPT-Realtime-2.1

GPT-Realtime-2.1 reasons over spoken requests, supports function tools and responds with streaming speech or text.

Call it with the model name openai/gpt-realtime-2.1/realtime on POST /jobs/createTask.

Introduction

GPT-Realtime-2.1 reasons over spoken requests, supports function tools and responds with streaming speech or text.

openai/gpt-realtime-2.1/realtime

Request parameters

ParameterRequiredDescription
speedNoSpeaking pace. ≥ 0.25 · ≤ 1.5 · Default: 1
promptNoDescribe what you want to make.
voice_idNoPick from the available voices. alloy · ash · ballad · coral · echo · sage · shimmer · verse · marin · cedar
max_tokensNoPer-turn output cap, including reasoning, text and audio tokens. ≥ 16 · ≤ 32000 · Default: 512
output_formatNoFile type of the result. pcm · g711_ulaw · g711_alaw
realtime_sessionNoAdvanced native session configuration; overlapping regular controls must agree. Function tools are executed by your application.
reasoning_effortNoReasoning effort for the spoken response; reasoning consumes output tokens. minimal · low · medium · high · xhigh
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
max_context_tokensNoRetained-history cap; this, the 4096-token instruction allowance and output must fit 128000. ≥ 512 · ≤ 123888 · Default: 4096
audio_noise_reductionNoInput denoising profile for a close microphone, room microphone, or preprocessed audio. near_field · far_field · none · Default: near_field

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 run
Standard$0.0048

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-Realtime-2.1 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-realtime-2.1/realtime 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-realtime-2.1/realtime",
  "input": {
    "prompt": "Calm ambient pads with a slow rising motif"
  }
}'

# 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-Realtime-2.1 API questions

What is the model name for GPT-Realtime-2.1 in the API?

Put openai/gpt-realtime-2.1/realtime for Realtime Voice in the model field of POST /jobs/createTask.

What are the limits of the GPT-Realtime-2.1 API?

Prompt length (characters): 4,096; Voices: 10. Requests outside these limits are rejected before anything is charged.

Can I try GPT-Realtime-2.1 without writing code?

Run GPT-Realtime-2.1 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-Realtime-2.1