---
title: "What are word and segment timestamps in speech-to-text?"
description: "ASR timestamps tell you when each word or segment was spoken. Word versus segment timestamps, how APIs return them, and what to do when an API returns plain text."
url: https://broadrouter.com/glossary/timestamps-asr/
lang: en
updated: 2026-11-16
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Timestamps (speech-to-text)

Updated 2026-11-16

Timestamps in speech-to-text are start and end times, in seconds, attached to parts of a transcript. Segment timestamps cover a phrase or sentence; word timestamps cover each word. They are needed for subtitles, search inside recordings and aligning text with speakers.

Also called: word timestamps, word-level timestamps, segment timestamps, timestamp\_granularities, ASR timestamps

A transcript tells you what was said; timestamps tell you where in the recording to find it.

## How it works

Most ASR systems offer two levels:

-   **Segment level.** One time range per phrase, for example `{"text": " Hi there!", "timestamp": (0.5, 1.5)}`.
-   **Word level.** One time range per word, for example `hi` at 0.5 to 0.9 s and `there` at 1.0 to 1.5 s.

Hugging Face’s ASR pipeline exposes both through `return_timestamps`: `True` gives segments for Whisper, `"word"` gives words, and CTC models such as Wav2Vec2 also support `"char"`. Results come back as `chunks`, each with `text` and a `(start, end)` tuple. The docs note that Whisper’s word times are estimated with dynamic time warping over cross-attention weights, an approximation rather than a measurement.

Hosted APIs follow the same pattern. OpenAI’s speech-to-text guide documents `timestamp_granularities[]` with `word` or `segment`, paired with `response_format: "verbose_json"`, and documents it only for the deprecated `whisper-1` model, which existing integrations can use until it shuts down on 26 February 2027.

```bash
curl https://api.openai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F model=whisper-1 -F file=@call.mp3 \
  -F response_format=verbose_json \
  -F "timestamp_granularities[]=word"
```

## Why it matters

-   **Subtitles.** SRT and VTT files need a start and end per caption line.
-   **Search and review.** A quality reviewer can jump to the second a complaint starts instead of listening to a whole call; see [transcribing call center recordings](https://broadrouter.com/blog/transcribe-call-center-recordings/).
-   **Speaker turns.** Merging a transcript with [diarization](https://broadrouter.com/glossary/diarization/) output works by matching times.
-   **Payload size.** Word-level output is much longer than the plain text, which matters if you then feed it to an LLM as [tokens](https://broadrouter.com/glossary/token/).

## On BroadNet Inference

BroadNet’s docs do not document timestamps. `/v1/audio/transcriptions` returns the transcript as `{"text": "..."}`, and no `timestamp_granularities` option is listed. BroadNet’s `/v1/models` metadata (checked 2026-11-15) lists `verbose_json` as a response format, but nothing says it carries segment or word times, so test it before relying on it. For coarse timing, cut the audio yourself, for example at pauses found with [voice activity detection](https://broadrouter.com/glossary/vad/) or into fixed segments, and record each chunk’s start offset. Each chunk’s text then inherits that offset. This gives sentence-level timing good enough for jumping around a call, not frame-accurate subtitles. Send `language` with every chunk to [BroadNet Transcribe Arabic](https://broadrouter.com/models/cohere-transcribe-arabic/) or [BroadNet Transcribe](https://broadrouter.com/models/cohere-transcribe/). If word-level timing is a hard requirement, run an aligner or a model that documents it.

## Questions

### What is the difference between word and segment timestamps?

A segment timestamp gives one start and end time for a phrase of one or more words. A word timestamp gives a time range for every word, which subtitle editors and search tools need.

### Does BroadNet's transcription API return timestamps?

No timestamps are documented. The response is {"text": ...} only, so split audio into chunks and track each chunk's offset if you need rough timing.

### How do I make subtitles without word timestamps?

Split the audio into short chunks at pauses, transcribe each, and use each chunk's start and end offset as the caption time. That gives phrase-level timing, enough for many subtitle files but not frame-accurate.

## See also

-   [Speech-to-text](https://broadrouter.com/glossary/speech-to-text/) (term)
-   [Speaker diarization](https://broadrouter.com/glossary/diarization/) (term)
-   [Voice activity detection (VAD)](https://broadrouter.com/glossary/vad/) (term)
-   [Sample rate](https://broadrouter.com/glossary/sample-rate/) (term)
-   [SRT subtitles](https://broadrouter.com/glossary/srt-subtitles/) (term)
-   [Arabic speech-to-text API, step by step](https://broadrouter.com/guides/arabic-speech-to-text-api/) (guide)
-   [How to transcribe call center recordings: an Arabic-ready pipeline](https://broadrouter.com/blog/transcribe-call-center-recordings/) (article)
-   [Whisper API alternative: when to switch, and how to test one](https://broadrouter.com/blog/whisper-api-alternative/) (article)
-   [Arabic subtitles (SRT) from a speech-to-text API: what you need](https://broadrouter.com/blog/arabic-subtitles-srt-api/) (article)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-timestamps-asr&utm_content=page-cta) ·

**Sources**

-   [OpenAI, speech to text guide (timestamp\_granularities) (checked 2026-11-16)](https://developers.openai.com/api/docs/guides/speech-to-text)
-   [Hugging Face Transformers, pipelines (ASR return\_timestamps) (checked 2026-11-16)](https://huggingface.co/docs/transformers/main_classes/pipelines)
-   [BroadNet Inference API reference, transcription response (checked 2026-11-16)](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-timestamps-asr&utm_content=sources)
