Workbench
Output
Ready for a new runRelated models and next tasks
Missing the model you need?
Two ways to transcribe speech
Key numbers
- Segment maximum
- 60s
What it does
Two ways to transcribe speech
GPT Transcribe accepts an unstructured context note, domain keywords and multiple expected languages. A context note can identify the subject under discussion, while vocabulary hints distinguish an unfamiliar product name from an ordinary word. The model can also use earlier transcribed turns within the continuing session, which is useful when a later phrase refers to a name established earlier. The committed-turn workflow gives an application an explicit point at which to close an audio segment. Transcript deltas can then populate a text preview until the final segment is available. This endpoint meters the final audio duration reported by the model; a caller chooses the maximum admitted segment length before sending samples. GPT Transcribe does not expose Live Transcribe’s adjustable delay profile on this connection. The language hints suit a discussion in which more than one language may appear. For example, a speaker might explain a release in English and then quote its French product name. Give the model the languages that actually occur in that material so that unusual words have plausible linguistic context. Keywords work at a different level from language choice. They can supply an organisation name, a device identifier or a technical term that people pronounce in different ways. A short description of the subject can accompany them. The file result contains the recognized speech as text suitable for searching and correcting.
Where it fits
Spoken data entry
For a spoken data-entry form using GPT Transcribe, let the user finish a field, commit that recording and show the resulting text for correction. Confirm identifiers or amounts in the application before saving them to the record.
Interview segment review
For an interview-review tool, send one bounded utterance at a time with a short description of the topic and names. Keep the association between each submitted segment and its completed text so a reviewer can revisit ambiguous passages.
Model reference
GPT Transcribe API reference
How to call the GPT Transcribe API
Prompt guide & Pro tips
Choose the file endpoint for a finished recording. Choose realtime transcription to receive text as each spoken turn is committed. Prepare GPT Transcribe context as background about the subject, audience or terminology. Supply the proper spelling of specialist names through keyword hints, and choose likely language codes when the conversation is multilingual. Do not use the context field to ask for a summary or an answer: the task is to recognize speech, so editorial processing should happen after the transcript is finalized. Use manual commits at clear utterance boundaries and keep each segment within the selected one-to-sixty-second limit. The streaming input must match 24 kHz mono 16-bit PCM or 8 kHz G.711; the short-WAV task preserves that same encoding. Review words that matter before triggering a workflow. Finalization occurs per segment, allowing the next segment to be admitted independently. This is the committed realtime-transcription endpoint; the separate file-transcription API has a different request format and is not implied by a WAV test task.
GPT Transcribe API questions
All GPT models18
Audio models7
GPT TranscribeCurrentSpeech to text · Realtime transcriptionOpenAI official price: $0.000075$0.000015per second of input audio
GPT Live TranscribeRealtime 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