by OpenAI

Identify who spoke in a recording and return time-aligned segments with speaker labels.

openai/gpt-4o-transcribe-diarize/speech-to-text
  • 184 languages
  • Speech to Text

About GPT-4o Transcribe Diarize

Identify who spoke in a recording and return time-aligned segments with speaker labels.

Call it with the model name openai/gpt-4o-transcribe-diarize/speech-to-text on POST /jobs/createTask, from $0.0001.

Introduction

Identify who spoke in a recording and return time-aligned segments with speaker labels.

openai/gpt-4o-transcribe-diarize/speech-to-text

Request parameters

ParameterRequiredDescription
audio_urlYesThe voice or music track to use.
languageNoThe language of the speech. aa · ab · ae · af · ak · am · an · ar · as · av · ay · az · ba · be · bg · bh · bi · bm · bn · bo · br · bs · ca · ce · ch · co · cr · cs · cu · cv · cy · da · de · dv · dz · ee · el · en · eo · es · et · eu · fa · ff · fi · fj · fo · fr · fy · ga · gd · gl · gn · gu · gv · ha · he · hi · ho · hr · ht · hu · hy · hz · ia · id · ie · ig · ii · ik · io · is · it · iu · ja · jv · ka · kg · ki · kj · kk · kl · km · kn · ko · kr · ks · ku · kv · kw · ky · la · lb · lg · li · ln · lo · lt · lu · lv · mg · mh · mi · mk · ml · mn · mr · ms · mt · my · na · nb · nd · ne · ng · nl · nn · no · nr · nv · ny · oc · oj · om · or · os · pa · pi · pl · ps · pt · qu · rm · rn · ro · ru · rw · sa · sc · sd · se · sg · si · sk · sl · sm · sn · so · sq · sr · ss · st · su · sv · sw · ta · te · tg · th · ti · tk · tl · tn · to · tr · ts · tt · tw · ty · ug · uk · ur · uz · ve · vi · vo · wa · wo · xh · yi · yo · za · zh · zu
temperatureNoVariation between takes. Higher is less predictable. ≥ 0 · ≤ 1

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$0.0001

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-4o Transcribe Diarize 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-4o-transcribe-diarize/speech-to-text 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-4o-transcribe-diarize/speech-to-text",
  "input": {
    "audio_url": "https://media.popnow.ai/shortfilm/voices/Aoede-46e4c427.mp3"
  }
}'

# 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-4o Transcribe Diarize API questions

How much does the GPT-4o Transcribe Diarize API cost?

GPT-4o Transcribe Diarize costs $0.0001 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-4o Transcribe Diarize in the API?

Put openai/gpt-4o-transcribe-diarize/speech-to-text for Speech to Text in the model field of POST /jobs/createTask.

What does a Diarize speaker label mean?

Diarize labels distinguish voices in one recording; they do not establish legal identity or match people across files.

Does Diarize include time ranges?

Segments include start and end times alongside speech, giving a reviewer a place to resume listening.

How are longer conversations segmented?

Automatic chunking handles longer recordings while the completed result keeps the conversation's segment order.

Can I supply names or voice references to Diarize?

This speaker-focused endpoint has no prompt, reference-voice or timestamp-granularity input; automatic chunking is applied for you.

What should I review before attributing a quote?

Crosstalk and rapid interruptions can confuse speaker boundaries, so attribution needs a listening check.

What are the limits of the GPT-4o Transcribe Diarize API?

Largest upload: 25 MB; Languages: 184. Requests outside these limits are rejected before anything is charged.

Can I try GPT-4o Transcribe Diarize without writing code?

Run GPT-4o Transcribe Diarize 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-4o Transcribe Diarize