Capabilities
Explore what GPT-4o Transcribe supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- OpenAI
- Product
- Speech-to-Text
- Release Date
- Mar 20, 2025
- Data Policy
- No training
- Region
- Global
- Input
- Audio
- Output
- Text
Playground
Try GPT-4o Transcribe by OpenAI. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for GPT-4o Transcribe.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| OpenAI | Not specified | Text | $0.0051 / minute | — | openai/gpt-4o-transcribe:openai |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 25000000 |
| Max seconds | 3600 |
| Formats | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm |
Provider Notes
Whisper 1 alone supports translation plus SRT/VTT and word/segment timestamp granularities. GPT-4o Transcribe and GPT-4o Mini Transcribe support JSON/text, prompting, logprobs, and completed-audio SSE. GPT-4o Transcribe Diarize is the only diarization model and uses chunking plus optional known-speaker references; it does not accept prompt or timestamp granularities. GPT-Realtime-Whisper is a separate realtime-only model fixed to mono 24 kHz PCM16.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=openai/gpt-4o-transcribe' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | openai/gpt-4o-transcribe — Required model identifier. |
chunking_strategy (auto or server_vad) | View Accepted Values |
include: [logprobs] (GPT-4o batch models) | View Accepted Values |
known_speaker_names / known_speaker_references (diarize model) | View Accepted Values |
stream (completed-audio SSE; GPT-4o batch models) | View Accepted Values |
delay / include item.input_audio_transcription.logprobs (gpt-realtime-whisper) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 25000000 |
| Max seconds | 3600 |
| Formats | flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| GPT-TranscribeOpenAI | Not specified | $0.0038 / minute | — |
| GPT-Realtime-WhisperOpenAI | Not specified | $0.0145 / minute | — |
| GPT-4o Mini Transcribe (2025-12-15)OpenAI | Not specified | $0.0026 / minute | — |
| GPT-4o Transcribe DiarizeOpenAI | Not specified | $0.0051 / minute | — |
| GPT-4o Mini TranscribeOpenAI | Not specified | $0.0026 / minute | — |
| Whisper 1OpenAI | Not specified | $0.0051 / minute | — |