Voice-activated AI chat interface for automating interactions. Offers universal integration via webhooks, supports over 60 languages, and requires no registration. Provides separate speech and text processing with high speech quality. Users can start new sessions and build workflows using templates.
Connect to any backend using only a Webhook; the connection is secured by authentication.
The integration of OpenAI Speech is built on high standards and sounds very natural.
Languages for both voice input and output are detected automatically by OpenAI.
Both spoken and written outputs can be different; there is also support for Markdown.
None of your data is being collected; settings and chat history are stored on your device.
The chat history is bound to a unique session ID which can be reused at any time.
Allows use of the STT and TTS functionality by providing an OpenAI API Token.
Enables communication with the custom agent by setting up a registered webhook.
Utilizes the microphone icon to record voice which is then transcribed and sent to the Agent. The response is read aloud once processed.
Allows interruption of speech output by interacting with the wave animation.
Lets users start a new session by clearing history and generating a new session ID.
Requires POST method for HTTP requests with specific header authentication.
Provides a template to connect with other existing agents, with instructions for setup.
Connect to any backend using only a Webhook; the connection is secured by authentication.
Integration of OpenAI Speech that is high quality and sounds very natural.
Supports both voice input and output in multiple languages, automatically detected by OpenAI.
Both spoken and written outputs can be different, with support for Markdown.
No data is being collected; settings and chat history are stored on your device.
Chat history is bound to a unique session ID, which can be reset anytime.
Set up OpenAI API Key and Webhook information. Necessary for the app to send and receive messages using the custom Agent.
Speak to the app using a microphone. It converts speech to text, sends it to the Agent, and receives a response for text to speech conversion.
Allows users to interrupt the speech response with a single tap.
Clears the history and starts a new session with a new Session ID.
Uses HTTP POST method for sending and receiving authentication and message data.
Provides a template for integrating with other existing agents using n8n workflows.