Audio Input

POST /stt

Audio Input

cURL

curl --request POST \
  --url https://backend-1.chatzy.ai/stt

200

{
  "transcript": "HELLO THERE\n"
}

Transcribes an audio input and returns a final transcription.

Conversations View:

Query Parameters

token · string · required

Temporary access token used to authenticate the endpoint.

This token is obtained from the /generate_secret endpoint. `

If the token is missing or invalid, the server will respond with a 401 Unauthorized error.

Example:

"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."

chatbot_id · string · required

UUID of the conversation AI Agent to which the message is sent.

Example:

"51de6a36-5532-49c2-888e-46754ce102ba"

client_message_key · string · required

Unique identifier (UUID) that groups multiple audio inputs under a single user message. This key is generated on the client side before sending audio and must be included in each /stt request. All audio transcriptions sharing the same client_message_key will later be mapped together with the finalized user message when sent to /get-inference.

Example:

"51de6a36-5532-49c2-888e-46754ce102ba"

Response

200 - application/json

Transcription generated successfully.

transcript · string

Final transcription text of the provided audio input.

Example:

"HELLO THERE\n"