word-level timestamps

By default a transcription is one block of text. Add timestamps: true and you also get every word located in time — plus the transcript grouped into runs of speech, ready for subtitles.

curl -X POST "https://geko--seta-serve-transcriber-api.modal.run/v1/transcribe?timestamps=true" \
  -H "Authorization: Bearer $GEKO_API_KEY" \
  -H "Content-Type: application/octet-stream" \
  --data-binary @call.wav

Timestamps are free. The alignment is a by-product of the same decode pass, and you are billed on audio_seconds whether you ask for it or not.

turning it on

import { Geko } from "@gekoai/sdk";
import { readFile } from "node:fs/promises";

const geko = new Geko({ apiKey: process.env.GEKO_API_KEY });

const out = await geko.stt.transcribe({
  audio: await readFile("call.wav"),
  filename: "call.wav",
  timestamps: true,
});

for (const w of out.words ?? []) {
  console.log(`[${w.start.toFixed(2)}–${w.end.toFixed(2)}] ${w.word}`);
}
// [0.20–0.72] сәлеметсіз
// [0.84–1.12] бе

# one word per line: start, end, word — tab-separated
npx @gekoai/sdk transcribe call.wav --words

# 0.20    0.72    сәлеметсіз
# 0.84    1.12    бе

curl -X POST ".../v1/transcribe?timestamps=true" \
  -H "Authorization: Bearer $GEKO_API_KEY" \
  -H "Content-Type: application/octet-stream" \
  --data-binary @call.wav

import requests

r = requests.post(
    "https://geko--seta-serve-transcriber-api.modal.run/v1/transcribe",
    params={"timestamps": "true"},
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/octet-stream",
    },
    data=open("call.wav", "rb").read(),
)

for w in r.json()["words"]:
    print(f"[{w['start']:.2f}-{w['end']:.2f}] {w['word']}")

what comes back

Everything from a normal transcription, plus two arrays:

{
  "text": "сәлеметсіз бе бүгін ауа райы өте жақсы",
  "model": "seta-kk-ru-v2",
  "audio_seconds": 45.1,
  "credits_charged": 113,

  "words": [
    { "word": "сәлеметсіз", "start": 0.2,  "end": 0.72 },
    { "word": "бе",         "start": 0.84, "end": 1.12 }
  ],

  "segments": [
    { "id": 0, "text": "сәлеметсіз бе",  "start": 0.2,  "end": 1.12 },
    { "id": 1, "text": "бүгін ауа райы", "start": 15.4, "end": 17.9 }
  ]
}

Word[]

Every word in the transcript, in order.

Show Word

string

The word. Lowercase and unpunctuated, like the rest of the transcript.

number

Seconds from the start of the audio — not from the start of a segment.

number

Seconds from the start of the audio.

Segment[]

The transcript grouped into runs of speech, split at the pauses used to chunk long audio.

Show Segment

number

Zero-based index, in playback order.

string

Text of this run.

number

The first word’s start.

number

The last word’s end.

Both fields are absent unless you pass the flag — not empty, absent. That is deliberate: adding timestamps can never change the response shape for code that did not ask for them. In TypeScript they are optional, so reach for out.words ?? [].

words or segments?

You are building	Use	Why
Subtitles, captions	`segments`	One cue per word is unwatchable
Click-a-word-to-seek transcript UI	`words`	You need per-word boundaries
Keyword search in a recording	`words`	Jump to the exact hit
Talk-time / silence analysis	`segments`	The gaps between runs are the pauses
Aligning to a waveform	either	`words` for detail, `segments` for structure

subtitles

toSubtitles() formats a transcription as SubRip (.srt) or WebVTT (.vtt). It is a pure function — no client, no API key, no request.

import { toSubtitles } from "@gekoai/sdk";
import { writeFile } from "node:fs/promises";

const out = await geko.stt.transcribe({ audio, timestamps: true });

await writeFile("call.srt", toSubtitles(out));         // SubRip
await writeFile("call.vtt", toSubtitles(out, "vtt"));  // WebVTT

npx @gekoai/sdk transcribe call.wav --srt > call.srt
npx @gekoai/sdk transcribe call.wav --vtt > call.vtt

# response_format works exactly as it does on Whisper
curl -X POST ".../v1/audio/transcriptions" \
  -H "Authorization: Bearer $GEKO_API_KEY" \
  -F file=@call.wav \
  -F response_format=srt

1
00:00:00,200 --> 00:00:01,120
сәлеметсіз бе

2
00:00:15,400 --> 00:00:17,900
бүгін ауа райы

On the OpenAI-compatible endpoint, response_format=verbose_json also returns segments and words, so Whisper code that already reads them keeps working.

how the alignment works

Seta is a CTC model. It reads the audio as a sequence of frames and emits a token — or a blank — for each one, so the frame index at which a token is emitted is its position in time. Grouping those tokens into words and multiplying by the frame duration gives the boundaries. Nothing is estimated after the fact and no second pass runs, which is why the feature is free. Audio longer than about 20 seconds is split at pauses before decoding. Each piece is timed independently and then shifted back into the timeline of the whole file, so start and end are always measured from the beginning of your audio, whatever its length.

Precision is bounded by the frame rate, so treat boundaries as accurate to a few tens of milliseconds — right for subtitles, search and seeking. It is not phoneme-level forced alignment.

Two consequences worth knowing:

Boundaries sit on speech, not silence. A segment starts at its first word and ends at its last, so the pause between segments is real silence.
A word’s end and the next word’s start differ. The gap is the actual pause between them, not padding.

limits


Extra cost	none — billed on `audio_seconds` either way
Max duration	2 hours per request, same as any transcription
Precision	tens of milliseconds
Speaker labels	not yet — diarization is on the roadmap

Drop-in for Whisper

verbose_json, srt and vtt all work on the OpenAI-compatible route.

Accuracy

8.71% WER on KSC2, including code-switched speech.

get started

text-to-speech

speech-to-text

guides

sdk

reference

word-level timestamps

turning it on

what comes back

words or segments?

subtitles

how the alignment works

limits

Drop-in for Whisper

Accuracy

​turning it on

​what comes back

​words or segments?

​subtitles

​how the alignment works

​limits

Drop-in for Whisper

Accuracy

turning it on

what comes back

words or segments?

subtitles

how the alignment works

limits