New Sign up free, 10 calls on us. Up to $1, no card needed.

Whisper v1

Released 2023-03-01

transcription

Whisper v1 is OpenAI's general-purpose speech recognition model, trained on a large dataset of diverse audio.

Input
audio
Output
text
Price
$0.006/min

Price in context

Where the price sits among 11 comparable models

Per minute$0.006/min
$0.002 · Fun-ASR Realtime Chirp 2 · $0.016

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Audio

Languages Trained on 98 languages; 57 listed as supported, the languages that met OpenAI's under-50% word-error-rate threshold across the transcriptions and translations endpoints
Audio limits
  • mp3/mp4/mpeg/mpga/m4a/wav/webm, up to 25MB
  • word- and segment-level timestamps (verbose_json), srt/vtt output
  • no streaming
  • only model supported on the translations endpoint (to English)
Speaker diarization No
Streaming transcription No
Timestamps Yes

Model

Modalities audio → text

Open-source Whisper large-v2 served via API; prompt limited to 224 tokens.

per OpenAI official docs ↗

Use Whisper v1 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/audio/transcriptions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("meeting.mp3", "rb"),
    language="en",
)
print(resp.text)

About Whisper v1

  • It is a multitask system that performs transcription, multilingual speech recognition, speech translation, and language identification, and is billed simply per minute of audio processed.
  • Despite newer GPT-4o-based transcription models, it is for several jobs still the only option in OpenAI's audio stack.
  • It is the sole model served on the translations endpoint, which renders speech into English, and the sole model supporting timestamp granularities at segment or word level.
  • It also has the widest response-format support of the family, covering JSON, plain text, verbose JSON, SRT, and VTT, which is what subtitle pipelines need.
  • The trade-offs are equally concrete: streamed transcription is not supported, prompts steer style rather than content (the model tends to mirror the punctuation and capitalization of the prompt), and only the final 224 tokens of a prompt are considered.
  • Shared transcription limits apply, with mp3, mp4, mpeg, mpga, m4a, wav, and webm accepted up to 25MB.
  • OpenAI's documentation now frames it historically, though the model page carries no deprecation notice.
  • Synthorai accepts Whisper jobs on its OpenAI-compatible /v1/audio/transcriptions route, so existing clients work as-is.

FAQ

Is the Whisper v1 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try Whisper v1 against your real workload before adding a payment method.

What is Whisper v1 best at?

Multitask: transcription, translation, language identification; billed simply per minute of audio; compatible across transcription and translation endpoints. See the About section for the full picture from the vendor's own release notes.

How much does Whisper v1 cost?

Whisper v1 costs $0.006 per minute of audio transcribed on Synthorai: pay-as-you-go, no platform markup, no subscription.

Which languages does Whisper v1 support?

Whisper v1 supports Trained on 98 languages; 57 listed as supported, the languages that met OpenAI's under-50% word-error-rate threshold across the transcriptions and translations endpoints. On Synthorai you call it through POST /v1/audio/transcriptions, the OpenAI transcription API shape.

How do I get access to Whisper v1?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="whisper-1", and you're done. One API key covers every model on the gateway.

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →