whisper-timestamped

by LINTO / Linagora

Word-level timestamps for OpenAI Whisper without retraining.

TL;DR

Word-level timestamps for OpenAI Whisper without retraining.

Best for subtitle authoring + karaoke pipelines that need per-word offsets. Pricing: free.

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

What it is

Cross-attention based forced alignment over Whisper's output to produce reliable word-level timings. AGPL-3.0 — note copyleft if you ship downstream.

Best for: Subtitle authoring + karaoke pipelines that need per-word offsets.
Watch out for: Slower than vanilla Whisper; cross-attention alignment imperfect at low SNR.

Install / use

pip install whisper-timestamped

Features

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

whisper-timestamped vs Whipscribe

Featurewhisper-timestampedWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to whisper-timestamped

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.