> ## Documentation Index
> Fetch the complete documentation index at: https://guide.omnia-voice.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Speech to text

> Transcribe audio files or live streams. No agent involved.

Transcription is available on its own, without building a voice agent. Send audio
in, get text back.

```
https://stt.omnia-voice.com
```

Authenticate with the same key you use for the rest of the API, in the
`X-API-Key` header.

|               | Endpoint           | Use it for                                    |
| ------------- | ------------------ | --------------------------------------------- |
| **Batch**     | `POST /transcribe` | Recordings, uploads, anything already on disk |
| **Streaming** | `wss://.../stream` | Live audio, as it is being spoken             |

Language is auto-detected — there is no language parameter to get wrong.

## Transcribe a file

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST "https://stt.omnia-voice.com/transcribe" \
    -H "X-API-Key: $OMNIA_API_KEY" \
    -H "Content-Type: audio/mpeg" \
    --data-binary @audio.mp3
  ```

  ```javascript Node.js theme={null}
  import { readFile } from "node:fs/promises";

  const audio = await readFile("audio.mp3");

  const res = await fetch("https://stt.omnia-voice.com/transcribe", {
    method: "POST",
    headers: {
      "X-API-Key": process.env.OMNIA_API_KEY,
      "Content-Type": "audio/mpeg",
    },
    body: audio,
  });

  const { transcript } = await res.json();
  console.log(transcript);
  ```

  ```python Python theme={null}
  import os, requests

  with open("audio.mp3", "rb") as f:
      res = requests.post(
          "https://stt.omnia-voice.com/transcribe",
          headers={
              "X-API-Key": os.environ["OMNIA_API_KEY"],
              "Content-Type": "audio/mpeg",
          },
          data=f,
      )

  print(res.json()["transcript"])
  ```
</CodeGroup>

### Response

```json theme={null}
{
  "transcript": "Hello, this is the transcribed text.",
  "duration_ms": 5230,
  "language": "en-US"
}
```

<ResponseField name="transcript" type="string">
  The full text.
</ResponseField>

<ResponseField name="duration_ms" type="integer">
  Audio length in milliseconds. This is what you are billed on.
</ResponseField>

<ResponseField name="language" type="string">
  The detected language.
</ResponseField>

## Audio formats

Send the matching `Content-Type` — `audio/mpeg` for MP3, `audio/wav` for WAV,
`audio/ogg`, `audio/webm`, `audio/mp4`.

<Tip>
  Quality in beats quality out. 16 kHz mono is plenty for speech and keeps
  uploads small; a noisy 48 kHz stereo recording transcribes worse than a clean
  16 kHz one, not better.
</Tip>

## Billing

4 credits per minute (\$0.04), rounded up, one-minute minimum. See
[Credits](/concepts/credits).

<Card title="Live streaming" icon="tower-broadcast" href="/speech-to-text/streaming">
  Transcribe audio as it is spoken, with interim results.
</Card>