Whisper
Whisper is OpenAI's general-purpose speech recognition model, trained on 680,000 hours of multilingual audio and able to transcribe speech, translate it to English, and identify languages as a single multitask model.
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/whisper-1'), audio: await readFile('audio.mp3'),});Playground
Try out Whisper 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.
WhisperSpeech 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 | 3.6s | 90tps | $5/M | $30/M | Read: $0.5/M Write: $6.25/M | $10/K + input costs | +4 |  | 07/09/2026 | |||
| 1.1M | 0.9s | 161tps | $1/M | $6/M | Read: $0.1/M Write: $1.25/M | $10/K + input costs | +4 | | 07/09/2026 | |||
| 1M | 0.5s | 136tps | $5/M | $30/M | Read: $0.5/M Write: — | $10/K + input costs | +4 |  | 04/24/2026 | |||
| 400K | 1.0s | 139tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10/K + input costs | +4 | | 03/17/2026 | |||
| 1.1M | 3.0s | 91tps | $2.50/M | $15/M | Read: $0.25/M Write: — | $10/K + input costs | +4 | | 03/05/2026 | |||
| 400K | 3.9s | 161tps | $0.25/M | $2/M | Read:$0.03/M Write:— | $14/K + input costs | +4 | | 08/07/2025 |
About Whisper
OpenAI released Whisper as an open-source speech recognition system in September 2022, trained on 680,000 hours of multilingual and multitask supervised data collected from the web. That scale and diversity made Whisper robust to accents, background noise, and technical language. The hosted API model, Whisper, arrived on September 21, 2022 alongside the GPT-3.5 Turbo API, serving the large-v2 weights through a managed endpoint.
Whisper is a multitask model. Beyond multilingual transcription, Whisper performs speech translation into English and language identification, so one model covers the common speech workflows without separate systems.
Because the underlying model is open source, Whisper became the reference point for speech-to-text across the industry. Teams that run open-source Whisper locally can use Whisper through AI Gateway for the hosted path, keeping output behavior familiar while gaining unified authentication, observability, and spend controls.
What To Consider When Choosing a Provider
- Configuration: Newer transcription models exist in the catalog:
gpt-4o-transcribeandgpt-4o-mini-transcribeimprove word error rate over Whisper-generation models. Whisper remains the pick when you want the multitask capabilities, duration-based pricing, or consistency with self-hosted open-source Whisper deployments. - 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 Whisper
Best for
- Multilingual transcription: One model handles many languages without per-language configuration
- Speech translation: Non-English audio translated directly into English text
- Language identification: Detecting the spoken language as a pipeline preprocessing step
- Duration-based billing: Costs scale with audio length, which simplifies budget modeling
- Open-source consistency: Hosted behavior that matches self-run Whisper deployments
Consider alternatives when
- Accuracy-critical transcripts:
gpt-4o-transcribeandgpt-4o-mini-transcribedeliver lower word error rates - Live voice experiences: The gpt-realtime family handles speech-to-speech conversation directly
- High-volume token pricing: The newer transcribe models bill by tokens if that fits your cost model better
Conclusion
Whisper remains the versatile workhorse of speech recognition: multilingual, multitask, and consistent with the open-source model the industry standardized on. Use Whisper through AI Gateway for translation and language identification, and reach for gpt-4o-transcribe when accuracy alone decides.