AI Voices - API Documentation

App Command (API Call)
POST your request to https://api.aiappsapi.com with your API key and account ID in the POST body. The fields described in each section below go inside the jsonData POST field as a JSON-encoded string. Use this method when your server is making the call and you have your API credentials available.

Mode / Webhook (Direct URL)
POST directly to the endpoint URL shown in each section. The fields go in the POST body as standard form fields (the same fields you would include in an HTML form POST). Use this method for provider webhooks, website forms, or any third-party system that sends form data. No API key is required - the account ID is part of the URL.

Converts text into spoken audio using AWS Polly. Returns the audio file as a base64-encoded string ready for playback or storage. Optionally returns lip-sync tween data containing frame-level viseme and word timing for driving avatar mouth animations alongside the audio.

You can pass voice settings directly in each request, or reference a saved character preset by its ID. Per-request fields override the character defaults, so you can use a preset as a baseline and change just what you need.

Converts audio into text using OpenAI Whisper. Send a base64-encoded audio file and receive a text transcript with language detection and duration. Supports common audio formats including WebM, MP3, WAV, and others accepted by the Whisper API.

This is the same transcription the AI Chatbot uses when voice input is enabled on a chat window. The chatbot automatically sends recorded audio through this command to convert spoken messages into text before processing them.

Returns a list of all available AWS Polly voices. Each voice includes its ID, display name, gender, language, and supported engines. Use this to find valid voice IDs for the getaudio command or to build a voice selector in your application. You can filter results by engine type or language code.

AI Voices integrates directly with the AI Chatbot through the platform's AppBridge system. When a chatbot has a voice character assigned, every response the chatbot generates is automatically converted to spoken audio and returned alongside the text. This works across all chatbot types and delivery methods including the embeddable chat widget, webhooks, and direct API calls.

Voice input: The embeddable chat widget includes a microphone button when voice is enabled. Users hold the button to record audio, which is sent to the gettranscription command to convert speech to text before the chatbot processes it. This gives you full two-way voice conversations through the chat window.

Voice output: When the chatbot generates a response, it reads the character's saved settings (voice, engine, format, language, tween preference) and calls getaudio internally. The base64 audio and any tween animation data are added to the chatbot response so your front end can play the audio and animate an avatar without any extra API calls.

The Voice Characters page in the admin panel lets you create and manage named voice presets. Each character saves a complete set of voice settings -- Polly voice ID, engine, output format, language code, text type, and whether to include tween data. Once saved, reference a character by its index number in any getaudio API call or assign it to a chatbot for automatic voice output.