Speech to Text

POST

https://api.async.com/speech_to_text

Upload an audio file and receive its transcript. This is the simplest way to transcribe pre-recorded audio.

Request

Header Params

Body Params multipart/form-dataRequired

Responses

🟢200Success

application/json

Bodyapplication/json

🟠401 INVALID_API_KEY

🟠400INVALID_LANGUAGE

🟠429USAGE_LIMIT_EXCEEDED

🟠429RATE_LIMIT_EXCEEDED

🟠429TOO_MANY_CONCURRENT_REQUESTS

Request Example

Shell

JavaScript

Java

Swift

curl --location 'https://api.async.com/speech_to_text' \
--header 'x-api-key: <api-key>' \
--header 'version: v1' \
--form 'file=@"cmMtdXBsb2FkLTE3ODMzMjQzMzg0MDAtMg==/example.wav"' \
--form 'model_id=""' \
--form 'language=""'

Response Example

200 - Example 1

{
    "text": "Hey, welcome back to another episode. So last week we talked about the future of work, and the response was overwhelming"
}

Modified at 2026-07-06 11:21:02

Speech to Text (WebSocket)

Clone Voice