openai/whisper-large-v3

Whisper V3 delivers high-accuracy speech recognition across 99 languages. Ideal for transcription, subtitles, and accessibility.

OpenAI Audio 30 Sec/Chunk
Get API Key
Try in Playground
Free Trial Credit No Credit Card Required
$1.00

api_example.sh

curl -X POST "https://platform.qubrid.com/api/v1/qubridai/audio/transcribe" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -F "model=openai/whisper-large-v3" \
  -F "file=@<YOUR-AUDIO-COMPLETE-PATH>"

Technical Specifications

Model Architecture & Performance

Model Size 1.55B params
Context Length 30 Sec/Chunk
Quantization fp16
Tokens/Second 386
Architecture Encoder-Decoder Transformer
Precision float16
License MIT
Release Date November 2023
Developers OpenAI

Pricing

Pay-per-use, no commitments

Processing Rate $0.0017/Minute

API Reference

Complete parameter documentation

Parameter Type Default Description
task select transcribe Choose whether to transcribe to the original language or translate to English.
language select en Select the spoken language (auto-detect if unsure).
temperature number 0 Controls randomness of output — 0.0 means deterministic.
initial_prompt string Business meeting conversation Guides the model to better understand the audio context.
word_timestamps boolean true Return per-word timestamps for the transcription.
vad_filter boolean true turn it on when you have long pauses or background noise, leave off for tightly trimmed clips to save compute.
return_segments boolean true Return transcription with time-segment metadata.
output_format select json Choose the transcription output format.

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
Multilingual
Timestamp support
Handles noisy input
Robust accuracy
Large model size
Slow for long files
Occasional misalignment

Use cases

Recommended applications for this model

Meeting notes
Podcasts
Customer support recordings
Accessibility
Subtitling

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid's medical OCR and research parsing cut our document extraction time in half. We now have traceable pipelines and reproducible outputs that meet our compliance requirements."

Clinical AI Team

Research & Clinical Intelligence