# `OpenrouterSdk.Api.Transcription`
[🔗](https://github.com/zmzlois/openrouter_sdk/blob/v0.1.0/lib/openrouter_sdk/api/transcription.ex#L1)

`POST /audio/transcriptions` — speech-to-text.

the upstream endpoint is openai-compatible: multipart upload with a
`file` part plus a `model` field.

    {:ok, %{"text" => text}} =
      OpenrouterSdk.Api.Transcription.create(%{
        file: {"recording.wav", File.read!("recording.wav"), "audio/wav"},
        model: "openai/whisper-1",
        language: "en"
      })

# `create`

```elixir
@spec create(
  map(),
  keyword()
) :: {:ok, map()} | {:error, OpenrouterSdk.Error.t()}
```

---

*Consult [api-reference.md](api-reference.md) for complete listing*