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

# Audio Input

Transcribes an audio input and returns a final transcription.

<img src="https://mintcdn.com/chatzyai/jXmVKZ3P6KCTbIH5/images/audio_input_1.png?fit=max&auto=format&n=jXmVKZ3P6KCTbIH5&q=85&s=759356a59df5ca1b4489035c1a20352b" alt="audio_input" width="495" height="377" data-path="images/audio_input_1.png" />

**Conversations View:**

<img src="https://mintcdn.com/chatzyai/jXmVKZ3P6KCTbIH5/images/audio_input_2.png?fit=max&auto=format&n=jXmVKZ3P6KCTbIH5&q=85&s=239c65f18cecf0601f6066d5dbc100c6" alt="audio_input" width="1316" height="674" data-path="images/audio_input_2.png" />


## OpenAPI

````yaml post /stt
openapi: 3.0.0
info:
  title: Chatzy AI API
  version: 1.0.0
  description: >-
    Chatzy AI REST API for messaging, contact conversations, and agent
    interactions.
  contact:
    name: Chatzy
    url: https://chatzy.ai
    email: support@chatzy.ai
servers:
  - url: https://vevdoh3hve.execute-api.us-east-1.amazonaws.com/prod
    description: Production Server
security: []
tags:
  - name: Authentication
    description: Authentication to access the API
  - name: Contact Conversations
    description: Get contact conversations
  - name: Conversational AI Agent Interactions
    description: Interact with the conversational AI agent
  - name: Authorized iframe Access
    description: APIs for authorized iframe access
paths:
  /stt:
    post:
      tags:
        - Conversational AI Agent Interactions
      summary: Audio Input
      parameters:
        - name: token
          in: query
          required: true
          description: >-
            **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.
          schema:
            type: string
            example: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...
        - name: chatbot_id
          in: query
          required: true
          description: UUID of the conversation AI Agent to which the message is sent.
          schema:
            type: string
            example: 51de6a36-5532-49c2-888e-46754ce102ba
        - name: client_message_key
          in: query
          required: true
          description: >-
            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`.
          schema:
            type: string
            example: 51de6a36-5532-49c2-888e-46754ce102ba
      responses:
        '200':
          description: Transcription generated successfully.
          content:
            application/json:
              schema:
                type: object
                properties:
                  transcript:
                    type: string
                    description: Final transcription text of the provided audio input.
                    example: |
                      HELLO THERE
      servers:
        - url: https://backend-1.chatzy.ai
          description: SSE Streaming Host

````