---
title: "Generates an speech to text transcription (not streamed)."
method: POST
path: "/v1/realtime/stt"
---

# Generates an speech to text transcription (not streamed).

`POST /v1/realtime/stt`

## Request body

- RtSttRequest
  - `audioBase64` string, required — The audio base64 string that contains the audio data. Audio data should be of type WAV.
  - `language` 'ar' | 'en'
  - `isEosEnabled` boolean — Whether to enable End of Speech detection or not.
  - `eosThreshold` number — The threshold value for End of Speech detection.
  - `model` 's2' | 's3' — The STT model to use for transcription.

## Response `200`

Successful response

- object
  - `text` string — The generated text of the speech audio list.

## Other responses

- `400` — Bad request
- `401` — Unauthorized
- `500` — Server Side Error

---

[API](https://skmtc.net/tryhamsa/apis/hamsa-api.md) · [All operations](https://skmtc.net/tryhamsa/apis/hamsa-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/tryhamsa/hamsa-api/versions/ecbeb5d8dc13/schema)