WaveNet (reference)

by DeepMind / community

DeepMind's seminal 2016 neural-vocoder paper — historical reference only.

Looking at WaveNet (reference)? Try this first.

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

TL;DR

Best for academic teaching and historical baseline for vocoder research. Pricing: free (community reproductions, varied licenses).

Category
Open source
License
NOASSERTION
Stars
★ 2.4k
Last push
2023-07-29
Pricing
free (community reproductions, varied licenses)
Platforms
Linux

What it is

WaveNet (DeepMind, 2016) is the paper that launched modern neural-vocoder work. The original code was never open-sourced; r9y9's MIT-licensed PyTorch reproduction is the most-used public re-implementation. Listed for historical completeness. Consent posture: vocoder architecture only — no end-user surface.

Best for: Academic teaching and historical baseline for vocoder research.
Watch out for: Original implementation never open-sourced by DeepMind; community reproductions vary in quality and licensing.

Install / use

git clone https://github.com/r9y9/wavenet_vocoder

Features

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

Links

GitHub repo ↗

WaveNet (reference) vs Whipscribe

FeatureWaveNet (reference)Whipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (community reproductions, varied licenses)$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages199
PlatformsLinuxWeb, API, MCP

Alternatives to WaveNet (reference)

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.