Zum Hauptinhalt springen
OpenAIJan 15, 2025

Whisper Large V3

openai/whisper-large-v3PrivateOpen weights

Whisper Large V3 is OpenAI’s open-weight speech recognition model, trained on about 5 million hours of audio and able to transcribe around 100 languages. It’s a robust general-purpose choice for multilingual transcription.

$0.36
per hour of audio
$0.006
per minute
25 MB
per file
One file, up to 25 MBminutes of audio
Opus in OGG or WebM32 kbps109
M4A or AAC64 kbps55
MP3128 kbps27
WAV16 kHz mono14
WAV44.1 kHz stereo2.5

Split a longer recording and send each part.

Quickstart

OpenAI-compatible: send the recording as a multipart file to the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/audio/transcriptions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-F model=openai/whisper-large-v3 \
-F file=@meeting.mp3
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
filewav, flac, m4a, aac, mp4, mp3, ogg, webmRequired, up to 25 MB
modelopenai/whisper-large-v3Required
response_formatjson | textDefault json
timestampstrue | falseAdds word or segment times to the JSON
languageAn ISO 639-1 code, such as enA hint; some models detect it themselves

Capabilities

Formatswav · flac · m4a · aac · mp4 · mp3 · ogg · webm
Timestampstimestamps: true
Language hintlanguage: "en"
OpenAI-compatibleclient.audio.transcriptions.create()
SubtitlesBuild them from timestamps; there is no SRT or VTT output
Failures are freeA failed transcription is not charged

Pricing

Billed per second of audio, in USD.

Per hour$0.36of audio
Per minute$0.006of audio
Per second$0.0001as billed

Estimate an archive

6,000 minof audio
$36.00to transcribe it

Against other transcription models

How it comparesamong 5 transcription models
Pricecheaper than 25%$0.36

Further right is better. Hover a dot for its model.

Specs

Model ID
openai/whisper-large-v3
Endpoint
POST /api/v1/audio/transcriptions
Formats
wav, flac, m4a, aac, mp4, mp3, ogg, webm
File
Up to 25 MB, sent as multipart
Output
json or text
Timestamps
Word or segment, depending on the model
Privacy
Private
Added
Jan 15, 2025

Compare

Every speech-to-text model on Venice, cheapest first.

ModelPrivacyPer minutePer hour
xAI Speech to Text v1Private$0.0019$0.1133
Parakeet ASRPrivate$0.006$0.36
Whisper Large V3Private$0.006$0.36
Wizper (Whisper v3)Private$0.006$0.36
ElevenLabs Scribe V2Anonymized$0.01$0.6012