---
title: "Word timestamps in speech recognition"
description: "Word timestamps are the start and end time of each word in a transcript. How models produce them, what affects accuracy, and how to get them from Phonon."
canonical: "https://www.fermionresearch.com/glossary/word-timestamps/"
source: "Fermion Research"
---

Glossary/facts checked 13 November 2026

# Word timestamps in speech recognition

The per-word timing behind subtitles, click-to-seek transcripts and redaction. Three ways systems produce it, and how to request it from the Phonon command line and server.

[Speech docs](https://www.fermionresearch.com/docs/speech/)

## The short answer

Word timestamps are the start and end times, in seconds from the beginning of the audio, that a speech recognition system attaches to each word of its transcript. They are what subtitle files, click-to-seek transcripts, audio redaction and speaker-labelled transcripts are built from.

Phonon-2.5, Phonon-2.5 English and Phonon-2 return them with fermion transcribe --json, and the server returns them in the OpenAI verbose_json shape.

## Three ways to get word timings

Where the times come from depends on the model family.

| Method | Where the times come from | Extra model needed | Public example |
| --- | --- | --- | --- |
| From the decoder's own alignment | CTC and transducer models emit tokens at specific audio frames, so each word's frames give its times | No | Parakeet TDT 0.6B v3 lists word-level timestamps on its card |
| Cross-attention plus dynamic time warping | The decoder's attention weights over audio frames are smoothed and aligned to tokens | No, but timing is indirect | Whisper's word_timestamps option (whisper/timing.py) |
| Forced alignment after transcription | A separate acoustic model aligns the finished text to the audio | Yes | WhisperX: voice activity detection plus forced phoneme alignment (Bain et al., 2023) |

## Getting word timestamps from Phonon

On the command line, --json returns a JSON object with the text, a start and end time per segment, and a words list with the start and end of every word in seconds from the start of the file.

On the server started with fermion serve, POST /v1/audio/transcriptions with response_format=verbose_json and timestamp_granularities=word returns a words list (word, start, end) and a segments list in the shape OpenAI clients expect. Uploads go up to 1 GB; the model handles utterances up to 30 seconds and decodes longer audio in chunks.

```text
fermion transcribe phonon-2.5 clip.wav --json
curl -s http://127.0.0.1:8000/v1/audio/transcriptions -F file=@clip.wav -F response_format=verbose_json -F timestamp_granularities=word
```

## What affects timing accuracy

- Frame resolution: a model's encoder looks at audio in fixed steps, so a word boundary cannot be placed more finely than one step.
- Fast or overlapping speech: when words run together, boundaries are ambiguous even for human annotators.
- Pauses and punctuation: some systems attach a pause to the previous word's end, others to the next word's start; check which before cutting audio.
- Long recordings: audio split into chunks needs each chunk's offset added back, which a well-built tool does for you.

To check timings on your own audio, compare them with a hand-marked or forced-aligned reference and measure the average gap at word starts and ends.

## Questions

## Related

- [Speech docs](https://www.fermionresearch.com/docs/speech/)
- [Server reference](https://www.fermionresearch.com/docs/server-reference/)
- [Transducer (RNN-T) vs CTC vs attention](https://www.fermionresearch.com/glossary/transducer-rnn-t/)
- [Offline speech recognition in Python](https://www.fermionresearch.com/speech/offline-speech-recognition-python/)
- [Self-host a speech-to-text server](https://www.fermionresearch.com/models/phonon-2-5/self-host/)

## Sources and method

- Phonon command line and server behaviour: Fermion Research docs (/docs/cli-reference/, /docs/server-reference/), read 2026-11-13.
- Whisper word timing: github.com/openai/whisper, whisper/timing.py, read 2026-11-13.
- Bain, Huh, Han, Zisserman, WhisperX: Time-Accurate Speech Transcription of Long-Form Audio, arXiv 2303.00747 (2023-03-01), read 2026-11-13.
- Parakeet TDT 0.6B v3 model card: huggingface.co/nvidia/parakeet-tdt-0.6b-v3, read 2026-11-13.

Canonical: https://www.fermionresearch.com/glossary/word-timestamps/

Source: [https://www.fermionresearch.com/glossary/word-timestamps/](https://www.fermionresearch.com/glossary/word-timestamps/)
