ONNX Runtime

by Microsoft

Microsoft's cross-platform inference runtime for ONNX-exported Whisper.

Looking at ONNX Runtime? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for production inference of Whisper / Wav2Vec2 / Parakeet across hardware. Pricing: free.

Category
Open source
License
MIT
Stars
★ 21.3k
Last push
2026-08-08
Pricing
free
Platforms
Linux, macOS, Windows, Android, iOS, Web

What it is

The standard ONNX runtime — supports CPU, CUDA, DirectML, CoreML, NNAPI. MIT.

Best for: Production inference of Whisper / Wav2Vec2 / Parakeet across hardware.
Watch out for: Whisper-specific decoders require custom export pipelines.

Install / use

pip install onnxruntime

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

Links

GitHub repo ↗

ONNX Runtime vs Whipscribe

FeatureONNX RuntimeWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOS, Windows, Android, iOS, WebWeb, API, MCP

Alternatives to ONNX Runtime

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 24.8k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.