GPT-4o Transcribe
GPT-4o Transcribe is a speech-to-text model built on the GPT-4o architecture, delivering lower word error rates and stronger language recognition than the original Whisper models for production transcription workloads.
import { experimental_transcribe as transcribe } from 'ai';import { gateway } from '@ai-sdk/gateway';import { readFile } from 'node:fs/promises';
const result = await transcribe({ model: gateway.transcriptionModel('openai/gpt-4o-transcribe'), audio: await readFile('audio.mp3'),});Playground
Try out GPT-4o Transcribe by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
GPT-4o TranscribeSpeech to text
Record a short clip from your microphone and the model transcribes it to text.
Record a clip to see the transcript here.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
More models by OpenAI
| Model |
|---|
| 1.1M | 3.9s | 51tps | $5/M | $30/M | Read: $0.5/M Write: $6.25/M | $10/K + input costs | +3 |  | 07/09/2026 | |||
| 1.1M | 1.2s | 142tps | $1/M | $6/M | Read: $0.1/M Write: $1.25/M | $10/K + input costs | +3 | | 07/09/2026 | |||
| 1M | 0.5s | 56tps | $5/M | $30/M | Read: $0.5/M Write: — | $10/K + input costs | +3 |  | 04/24/2026 | |||
| 400K | 1.1s | 135tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10/K + input costs | +3 | | 03/17/2026 | |||
| 1.1M | 2.8s | 96tps | $2.50/M | $15/M | Read: $0.25/M Write: — | $10/K + input costs | +3 | | 03/05/2026 | |||
| 131K | 0.2s | 160tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — |   +5 | 08/05/2025 |
About GPT-4o Transcribe
GPT-4o Transcribe launched on March 13, 2024 as part of OpenAI's next-generation audio models for the API. The model builds on the GPT-4o architecture and was extensively pretrained on specialized audio-centric datasets.
GPT-4o Transcribe improves word error rate over the Whisper model family across established benchmarks. On the FLEURS multilingual benchmark, GPT-4o Transcribe outperforms Whisper v2 and Whisper v3 across language evaluations. OpenAI attributes the advances to targeted reinforcement learning and midtraining with diverse, high-quality audio.
The practical effect is fewer misrecognitions in the conditions that break transcription products: heavy accents, noisy rooms, and varying speech speeds. Through AI Gateway, GPT-4o Transcribe runs behind the same key, observability, and spend controls as the rest of your model traffic.
What To Consider When Choosing a Provider
- Configuration: Audio support on AI Gateway is in beta. GPT-4o Transcribe runs through the AI SDK's
transcribefunction, which accepts a file buffer, base64 string, or URL. For high-volume pipelines where cost per request dominates, benchmarkgpt-4o-mini-transcribefirst; the mini variant often gets close on clean audio. - Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use GPT-4o Transcribe
Best for
- Production transcription quality: Word error rate directly affects the product and cleanup budgets
- Challenging audio conditions: Heavy accents, background noise, and variable speech speeds
- High-stakes transcripts: Support, sales, and compliance recordings where misrecognitions carry real cost
- Multilingual workloads: Strong FLEURS benchmark results across language evaluations
Consider alternatives when
- Cost-driven pipelines:
gpt-4o-mini-transcribehandles clean audio well at a lower rate - Speech translation needs:
whisper-1covers translation to English and language identification - Live voice agents: The gpt-realtime family handles speech-to-speech conversation directly
Conclusion
GPT-4o Transcribe is the model to reach for when transcript quality is the product. Route requests through AI Gateway with the AI SDK's transcribe function, and keep gpt-4o-mini-transcribe in reserve for the high-volume, cleaner-audio side of the pipeline.