About Whisper Large v3 Turbo

Controlled Whisper Large v3 Turbo transcription with multilingual ASR, translation, VAD, timestamps, subtitles, hotwords, and decoder controls.

Also known as Whisper Large Turbo, Whisper-Large-v3-Turbo

transcriptiontranslationmultilingualword timestampshotwordssrt vtt

Whisper Large v3 Turbo specs

Model ID: whisper-large-v3-turbo
Provider: OpenAI
Category: Transcription
Input: audio
Output: text
Endpoints: POST /v1/audio/transcriptions

Whisper Large v3 Turbo API pricingSave up to 17%

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

Type

Spec

Rate

Controlled transcription

per minute of audio

$0.006$0.005

Compare on the full pricing page

How to call the Whisper Large v3 Turbo API

Whisper Large v3 Turbo runs through POST /v1/audio/transcriptions. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Get an API key from the EmpirioLabs dashboard.

cURL: submit the job

curl https://api.empiriolabs.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "whisper-large-v3-turbo",
    "audio_url": "https://example.com/meeting-recording.mp3"
  }'

cURL: poll for the result

curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY"

Python

import requests

response = requests.post(
    "https://api.empiriolabs.ai/v1/audio/transcriptions",
    headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
    json={
        "model": "whisper-large-v3-turbo",
        "audio_url": "https://example.com/meeting-recording.mp3",
    },
)
job = response.json()

# Generation runs as an async job. Poll until it completes.
import time
while True:
    status = requests.get(
        f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
        headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
    ).json()
    if status.get("status") in ("completed", "failed"):
        print(status)
        break
    time.sleep(5)

Full Whisper Large v3 Turbo API reference

Whisper Large v3 Turbo API parameters

Request parameters supported by the Whisper Large v3 Turbo API on EmpirioLabs. Defaults apply when a field is omitted.

Parameter	Type	Default	Range / values	Description
audio_url	string	-	-	URL of the audio file to transcribe. Mutually exclusive with audio_base64.
audio_base64	string	-	-	Base64-encoded audio bytes. Mutually exclusive with audio_url.
audio_suffix	string	.audio	-	File extension hint (mp3, wav, m4a, etc.) when the audio source has no recognizable extension.
language	string	-	-	ISO 639-1 language code (en, es, fr, etc.). Leave blank for auto-detection.
task	enum	transcribe	transcribe, translate	transcribe = same language, translate = translate to English.
beam_size	integer	5	1 to 32	Beam search width. Higher = more accurate but slower.
best_of	integer	5	1 to 32	Number of candidates to sample with temperature > 0.
patience	number	1	0 to 10	Beam search patience factor. Higher = explore more candidates.
length_penalty	number	1	-10 to 10	Penalty applied to longer transcripts. Negative encourages shorter output.
repetition_penalty	number	1	0.1 to 5	Penalty for repeating tokens. >1 reduces repetition.
no_repeat_ngram_size	integer	0	0 to 20	Block any n-gram of this size from repeating in the output.
temperature	string	0,0.2,0.4,0.6,0.8,1	-	Sampling temperature. 0 = deterministic, higher = more variation.
compression_ratio_threshold	number	2.4	-	Treat output with compression ratio above this as failed and retry.
log_prob_threshold	number	-1	-	Treat segments with average log-prob below this as failed and retry.

24 more parameters in the docs

Good to know

Supports URL/base64 audio, language/task, beam and temperature fallback controls, VAD/chunking, hotwords, prompts, word timestamps, punctuation controls, token debug output, and JSON/text/SRT/VTT formats.

Whisper Large v3 Turbo API: common questions

How much does the Whisper Large v3 Turbo API cost?

On EmpirioLabs, Whisper Large v3 Turbo is billed pay as you go: Controlled transcription $0.005 (was $0.006) per minute of audio. The live rate card on this page always matches what the API charges.

Which endpoint does Whisper Large v3 Turbo use?

Whisper Large v3 Turbo is served through POST /v1/audio/transcriptions on api.empiriolabs.ai with standard bearer-token authentication.

Can I try Whisper Large v3 Turbo in the browser before integrating?

Yes. The EmpirioLabs playground runs Whisper Large v3 Turbo in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Whisper Large v3 Turbo API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.

Whisper Large v3 Turbo API