Workbench
Output
Ready for a new runRelated models and next tasks
Missing the model you need?
GPT Live Transcribe emits text while audio arrives, with language hints, vocabulary context and adjustable transcript delay.
Key numbers
- Segment maximum
- 60s
What it does
Captions before the speaker finishes
A tunable delay controls how long GPT Live Transcribe waits before emitting transcript text. A shorter delay can make a caption display feel more immediate, while a larger delay gives the model more speech to consider before showing a new fragment. Treat intermediate text as provisional in the interface, then use the committed segment’s final transcript for downstream processing. Free-form context can describe a meeting topic or a product discussion, while keyword hints can identify names that ordinary vocabulary does not cover well. Multiple language hints help with multilingual speech and code-switching. These are recognition aids, not commands to replace what the speaker said. Live Transcribe produces text rather than a spoken answer and does not provide speaker labels, word timestamps or confidence scores.
Where it fits
Live webinar captions
For a live webinar caption panel using GPT Live Transcribe, send short microphone chunks and keep the current segment visually distinct from finalized captions. Commit at an application-controlled boundary so an editor can associate final text with the correct portion of the session.
Terminology-aware operator console
For an operator console, supply the expected product names and likely languages before speech begins. Let the operator review completed segments before they become a stored case note or trigger an application workflow.
Model reference
GPT Live Transcribe API reference
How to call the GPT Live Transcribe API
Prompt guide & Pro tips
Describe the subject of the audio to GPT Live Transcribe in a short context note, then list relevant terms with their normal spelling. Avoid supplying a guessed full transcript: it can bias recognition toward words that were never spoken. If two languages are likely to alternate, provide both hints and check names, numbers and sentence boundaries with representative audio. Choose a delay profile using real listening conditions, including brief pauses and background noise. This connection uses explicit commits, not automatic turn detection; select a segment limit between one and sixty seconds and commit before that limit when a natural boundary occurs. PCM must be 24 kHz, 16-bit mono, or use 8 kHz G.711. A short matching WAV can exercise one segment in the task interface. Use the final reported audio duration for billing, and retain only the transcript your application actually needs.
GPT Live Transcribe API questions
All GPT models18
Audio models7
GPT TranscribeSpeech to text · Realtime transcriptionOpenAI official price: $0.000075$0.000015per second of input audio
GPT Live TranscribeCurrentRealtime transcriptionOpenAI official price: $0.00028$0.00006per second of input audio
GPT-Realtime-2.1 MiniRealtime conversationin OpenAI official price: $0.60$0.12out OpenAI official price: $2.40$0.48in OpenAI official price: $10$2out OpenAI official price: $20$4in OpenAI official price: $0.80$0.16per 1 million tokens
GPT-Realtime-2.1Realtime conversationin OpenAI official price: $4$0.80out OpenAI official price: $24$4.80in OpenAI official price: $32$6.40out OpenAI official price: $64$12.80in OpenAI official price: $5$1per 1 million tokens
GPT-4o Transcribe DiarizeSpeech to text$0.0001per second of input audio
GPT-4o TranscribeSpeech to text$0.0001per second of input audio
GPT-4o Mini TranscribeSpeech to text$0.00005per second of input audio
Text models11
GPT 6.1 TerraNewChatSoftened — This model answers instead of refusing, but requests beyond its own limits come back toned down, even with a fiction-writing system prompt. The call still succeeds and is still billed, so read the reply rather than trusting the status code.in $1out $5per 1 million tokens
GPT 6.1 SolChatSoftened — This model answers instead of refusing, but requests beyond its own limits come back toned down, even with a fiction-writing system prompt. The call still succeeds and is still billed, so read the reply rather than trusting the status code.in $2out $10per 1 million tokens
GPT 6 LunaChatin $0.10out $0.50per 1 million tokens
GPT 6 SolChatin OpenAI official price: $2$1.60out OpenAI official price: $10$8per 1 million tokens
GPT 6 AstraChatin OpenAI official price: $10$8out OpenAI official price: $50$40per 1 million tokens
GPT 5.6 LunaChatin OpenAI official price: $0.20$0.16out OpenAI official price: $1.20$0.96per 1 million tokens
GPT 5.6 SolChatin OpenAI official price: $5$4out OpenAI official price: $30$24per 1 million tokens
GPT 5.6 TerraChatin OpenAI official price: $2$1.60out OpenAI official price: $12$9.60per 1 million tokens
GPT-5.5Chatin OpenAI official price: $5$4out OpenAI official price: $30$24per 1 million tokens
GPT-5.4 MiniChatin OpenAI official price: $0.75$0.60out OpenAI official price: $4.50$3.60per 1 million tokens
GPT-5.4Chatin $2.50out $15per 1 million tokens