> ## Documentation Index
> Fetch the complete documentation index at: https://docs.geko.sh/llms.txt
> Use this file to discover all available pages before exploring further.
# speech-to-text that handles code-switching
> send audio, get Kazakh and Russian text back — including speakers who switch language mid-sentence. same API key as text-to-speech.
**Seta** turns speech into text. Send audio, get a transcript. It recognises **Kazakh and Russian** (model `seta-kk-ru-v2`), and — unlike every general-purpose ASR — it handles a speaker **switching between them mid-sentence**, because it was never asked to pick one.
Your existing key works. **One API key covers text-to-speech and speech-to-text, and both draw down the same credit balance** — nothing new to provision.
8.71% WER on KSC2. Whisper large-v3 scores 44.95% on the same audio.
Change `baseURL` on your OpenAI client. That's the whole migration.
## try it in one line
```bash theme={null}
export GEKO_API_KEY=sk-tokay-...
npx @gekoai/sdk transcribe call.wav
```
The transcript goes to stdout and the cost line to stderr, so `> transcript.txt` captures only the text.
## from code
```ts TypeScript theme={null}
import { Geko } from "@gekoai/sdk";
import { readFile } from "node:fs/promises";
const geko = new Geko({ apiKey: process.env.GEKO_API_KEY });
const { text, audio_seconds, credits_charged } = await geko.stt.transcribe({
audio: await readFile("call.wav"),
filename: "call.wav",
});
console.log(text); // сәлеметсіз бе бүгін ауа райы өте жақсы
console.log(audio_seconds, credits_charged); // 2.84 8
```
```bash curl theme={null}
curl -X POST "https://geko--seta-serve-transcriber-api.modal.run/v1/transcribe" \
-H "Authorization: Bearer $GEKO_API_KEY" \
-H "Content-Type: application/octet-stream" \
-H "x-filename: call.wav" \
--data-binary @call.wav
```
```python Python theme={null}
import requests
r = requests.post(
"https://geko--seta-serve-transcriber-api.modal.run/v1/transcribe",
headers={"Authorization": f"Bearer {KEY}", "x-filename": "call.wav"},
data=open("call.wav", "rb").read(),
)
print(r.json()["text"])
```
Or skip the upload entirely and let the server fetch it:
```ts theme={null}
const { text } = await geko.stt.transcribe({ url: "https://example.com/call.mp3" });
```
## what comes back
```json theme={null}
{
"text": "сәлеметсіз бе бүгін ауа райы өте жақсы",
"model": "seta-kk-ru-v2",
"audio_seconds": 2.84,
"processing_seconds": 0.153,
"rtf": 0.0539,
"x_realtime": 18.5,
"chunks": 1,
"sample_rate_in": 24000,
"credits_charged": 8
}
```
`audio_seconds` is what you pay for. `x_realtime` is how many times faster than real time the transcription ran.
Transcripts are **lowercase and unpunctuated**. That is not post-processing — the model's output vocabulary contains no capitals and no punctuation, so nothing is being stripped. Punctuation and truecasing are on the [roadmap](/roadmap).
## why there is no `language` parameter
Kazakh and Russian share one 70-character output vocabulary — the full Kazakh alphabet (42 letters), the full Russian alphabet (33), and Latin `a–z`. Both languages live in the same output space, so the model never has to be told which one it is hearing, and a speaker can switch **inside a single word** without the model switching anything.
This is the whole architectural bet, and it is why Seta is not built on Whisper. Whisper must be told one language per utterance, which makes genuine code-switching impossible to represent, and it scores 37–49% WER on Kazakh regardless. See [accuracy](/stt/accuracy) for the head-to-head.
`language`, `prompt` and `temperature` **are** accepted on the OpenAI-compatible endpoint, and ignored, so existing clients keep working.
## audio you can send
| | |
| ---------------- | --------------------------------------------------------- |
| **Containers** | anything `ffmpeg` reads — wav, mp3, m4a, flac, ogg, opus |
| **Sample rate** | any; resampled server-side to 16 kHz |
| **Channels** | any; downmixed to mono |
| **Max duration** | **2 hours** per request (longer returns `413` — split it) |
| **Long audio** | split automatically at pauses, not mid-word |
Telephony audio is fine: on simulated 8 kHz G.711 μ-law, accuracy drops only **8% relative** (8.71% → 9.41% WER), versus the 30–80% typical for models not adapted to narrowband.
## what it costs
| | |
| -------------- | ----------------------------------------------------- |
| **Rate** | **\$0.36 per hour of audio** |
| **In credits** | 2.5 credits per audio-second — 9,000 per audio-hour |
| **Billed on** | `audio_seconds`, rounded up, successful requests only |
Same credit pool as text-to-speech. Estimate before you spend, with no request:
```ts theme={null}
geko.stt.estimateCredits(3600); // 9000 credits === $0.36
```
Out of credits returns **HTTP 429** on *both* products, since it is one balance. The catalog endpoints (`/v1/models`, `/health`) are open and free.
## latency and cold starts
Warm, a short clip transcribes in **\~0.15 s** (about 18× real time). The GPU scales to zero when idle, so the **first** request after a quiet period pays a cold start of roughly 20–30 s — and the first transcription in a fresh container costs \~1.9 s while CUDA kernels warm up. If you need predictable latency for a demo or a call window, ask us to pin a warm container.
Per-domain WER, telephony, and comparisons against Whisper and ISSAI.
One balance across both products.
`geko.stt.transcribe(...)`, typed end to end.
Durations, rate limits, and cold starts.