Frequently Asked Questions
Find answers to common questions about Whissle's AI assistant, voice and text metadata APIs, and platform.
- Home
- Frequently Asked Questions
Frequently asked questions
Everything you need to know about Whissle — from the personal AI assistant to our speech-to-text and text intelligence APIs.
What is Whissle?
Whissle is a personal AI assistant that combines real-time voice intelligence, deep research, live call coaching, smart notes, and daily briefings. It works across web (lulu.whissle.ai), macOS desktop app, and as an API for developers.
What metadata does the Whissle Speech-to-Text API extract?
Beyond transcription, Whissle STT extracts rich metadata in a single pass — intent detection, emotion recognition, named entity recognition (NER), speaker diarization, age and gender estimation, and punctuation. The same metadata is also available for text input via our Text Intelligence API.
How does Whissle compare to other speech-to-text APIs?
Whissle's META-1 model performs transcription and metadata extraction simultaneously in a single pass, unlike traditional pipelines that require separate models for each task. This results in lower latency, lower cost, and richer output — all from one API call.
Is Whissle free to use?
Yes — the personal AI assistant at lulu.whissle.ai is free to use. The Speech-to-Text and Intelligence APIs have usage-based pricing starting at $0.003 per minute. Self-hosting via Docker is also available at no cost.
Can I self-host Whissle?
Absolutely. Whissle provides a full Docker Compose setup that runs the frontend, gateway (ASR + agent + proxy), and backend locally. It replaces cloud dependencies with SQLite and local storage, requiring only 16 GB RAM and a Gemini API key.
What is Live Assist / call coaching?
Live Assist provides real-time AI coaching during phone calls or meetings. It listens to the conversation, detects intent and emotion, and surfaces contextual suggestions, key points, and action items — all in real time with low latency.
What languages does Whissle support?
Whissle currently supports English with high-accuracy models (300M and 600M parameter variants). Multi-language support for Spanish, German, French, and other major languages is available through the 1.1B parameter model. Translation covers any-to-any language pairs.
How do I integrate Whissle into my application?
You can integrate via the JavaScript SDK (npm install @whissle/sdk), the REST API (api.whissle.ai), or self-host using Docker. The SDK provides streaming ASR, voice intelligence, and behavioral profiling out of the box for web and Node.js applications.