AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Productivity › whisper-timestamped
✦ Free & open sourceProductivity

whisper-timestamped

Multilingual speech recognition library adding word-level timestamps, confidence scores, and VAD to OpenAI Whisper.

Precise word-level timestamps for OpenAI Whisper transcripts

Extract word alignments and confidence scores from audio without extra neural alignment models.

Free forever · open source · AGPL-3.0
✓ Needs IT✓ Browser-based✓ Real-time collaboration
7.3
ZEKAI
Essential Whisper alignment tool
Free & open source · Productivity
Ease of setup5
Usefulness8
Maintenance8.5
Community7.5
★ 2,861
GITHUB
Sep 2026
UPDATED
AGPL-3.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

whisper-timestamped is a Python wrapper for OpenAI's Whisper speech recognition models. It extracts word-level timestamps and confidence scores directly from cross-attention weights. Technical professionals and automated workflows can use it to build timestamp-accurate transcriptions for meetings, interviews, and media archives.

Runs on
Cross-platform
Hosting
Self-host
Languages
Python
License
AGPL-3.0

What it is

This package modifies Whisper's transcription pipeline to compute exact start and end times for every spoken word. It includes integrated Voice Activity Detection to prune silence before decoding, preventing repetitive text hallucinations on silent audio. Additionally, it outputs confidence scores per word and handles speech disfluencies without requiring separate alignment networks.

Who it's for

This tool suits software engineers, technical executive assistants, and media specialists who need word-level audio alignment for subtitles, indexing, or automation scripts. It does not suit non-technical users looking for an out-of-the-box graphical desktop application.

Key features

Word-level timestamp extraction

Uses Dynamic Time Warping on cross-attention weights to calculate start and end times for individual spoken words.

Integrated Voice Activity Detection

Filters out silence using Silero or Auditok VAD prior to transcription, preventing hallucinated text output.

Per-word confidence scoring

Assigns explicit reliability metrics to each word and segment to highlight potential transcription errors.

Low-memory alignment execution

Computes alignments on the fly during decoding rather than running separate alignment networks, saving memory.

How to start

Up and running in 3 steps

1
Install system dependencies like ffmpeg and ensure Python 3.9+ is available.
2
Install whisper-timestamped via pip along with PyTorch and optional dependencies like onnxruntime.
3
Run whisper_timestamped from your terminal or call whisper_timestamped.transcribe() in Python scripts.
Real talk

Our honest verdict

What's great

  • Outputs word-level timing and confidence scores directly within standard Whisper data structures.
  • Prevents phantom text on quiet sections by executing pre-decoding Voice Activity Detection.
  • Does not require language-specific secondary alignment models like wav2vec.
  • Works via both a Python API and command-line execution.

Where it falls short

  • Requires local computing hardware and PyTorch, demanding a dedicated GPU for fast processing.
  • Lacks a graphical user interface, requiring command-line or script integration.
  • Can slow down decoding speeds slightly compared to default Whisper implementations.
  • Installation requires system-level audio dependencies like ffmpeg.
Cost

Pricing & license

The package is free under the AGPL-3.0 licence. Running costs depend entirely on your local GPU hardware or cloud server deployment.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: whisper-timestamped for Productivity
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure whisper-timestamped for you — and train your team.
Get it done for you ↗
Questions

FAQ

How does whisper-timestamped differ from stock OpenAI Whisper?

Standard Whisper provides approximate 1-second segment timestamps. whisper-timestamped extracts exact timing for each individual word.

Does it require external alignment models?

No. It computes alignment from cross-attention layers during inference, avoiding external wav2vec models.

Can I run this on CPU?

Yes. CPU execution is supported via PyTorch CPU packages or the provided CPU Dockerfile, though processing will take longer.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Productivity — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google