Descript Audio Codec

by Descript

High-quality neural audio codec — alternative to EnCodec.

TL;DR

High-quality neural audio codec — alternative to EnCodec.

Best for speech-LM tokenization with very high audio fidelity. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Windows

What it is

Descript's open neural audio codec. MIT.

Best for: Speech-LM tokenization with very high audio fidelity.
Watch out for: Codec only.

Install / use

pip install descript-audio-codec

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

Descript Audio Codec vs Whipscribe

FeatureDescript Audio CodecWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages199
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to Descript Audio Codec

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 22.3k

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.