> ## Documentation Index
> Fetch the complete documentation index at: https://docs.neosantara.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# Audio & Transkripsi

> Transkripsi file suara menjadi teks menggunakan model Whisper-1 dan Whisper Large.

Endpoint `/v1/audio/transcriptions` menyediakan paritas penuh dengan format OpenAI Audio API untuk transkripsi audio multibahasa.

<CodeGroup>
  ```python Python (OpenAI SDK) icon="python" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  from openai import OpenAI
  import os

  client = OpenAI(
      base_url="https://api.neosantara.xyz/v1",
      api_key=os.environ["NEOSANTARA_API_KEY"]
  )

  with open("rekaman.mp3", "rb") as audio_file:
      transcription = client.audio.transcriptions.create(
          model="whisper-large-v3-turbo",
          file=audio_file,
          language="id",
          response_format="json"
      )

  print(transcription.text)
  ```

  ```bash cURL icon="terminal" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  curl -X POST https://api.neosantara.xyz/v1/audio/transcriptions \
    -H "Authorization: Bearer $NEOSANTARA_API_KEY" \
    -F file="@rekaman.mp3" \
    -F model="whisper-large-v3-turbo" \
    -F language="id"
  ```
</CodeGroup>

## Parameter Transkripsi

| Parameter         | Tipe     | Wajib    | Keterangan                                                                       |
| :---------------- | :------- | :------- | :------------------------------------------------------------------------------- |
| `file`            | `binary` | Ya       | File audio dalam format multipart/form-data.                                     |
| `model`           | `string` | Ya       | `whisper-large-v3-turbo` atau `whisper-1`.                                       |
| `language`        | `string` | Opsional | Kode bahasa ISO-639-1 (contoh: `id` untuk Bahasa Indonesia, `en` untuk Inggris). |
| `prompt`          | `string` | Opsional | Petunjuk konteks atau ejaan istilah khusus (glossary).                           |
| `response_format` | `string` | Opsional | Format respons: `json`, `text`, atau `verbose_json`.                             |
| `temperature`     | `number` | Opsional | Nilai sampling antara `0` dan `1`. Default `0`.                                  |

## Format Berkas yang Didukung

* Audio: `mp3`, `mp4`, `m4a`, `wav`, `webm`, `ogg`, `flac`.
* Ukuran berkas maksimum standar: 25 MB per permintaan.


## Related topics

- [Chat Completions](/id/gateway/chat-completions.md)
- [Katalog Model](/id/gateway/models.md)
- [Manajemen File](/id/gateway/operations/files.md)