CassetteAI

What is CassetteAI?

CassetteAI is a generative audio API that produces music and sound effects at 44.1 kHz stereo for developers integrating audio into games, creator apps, and real-time pipelines. It renders a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. Access requires an API key through the fal.ai SDK or cURL, while a guest playground allows testing without signup.

What are the features of CassetteAI?

• Adaptive music generation

  Produces 1- to 4-minute tracks from prompts specifying mood, genre, or reference, outputting 44.1 kHz stereo .wav files with deterministic seeds.
• Sound effect generation

  Creates loopable clips from 100 milliseconds to 30 seconds based on text descriptions, supporting per-frame re-rolls.
• Unified API structure

  Uses a single call shape via fal.subscribe() to switch between the CassetteAI/music-generator and cassetteai/sound-effects-generator model identifiers.
• Guest playground

  Provides a web interface with preset prompts to generate and download .wav samples without creating an account.
• Text-to-speech (upcoming)

  A planned modality featuring zero-shot voice cloning from a 10-second sample and inline emotion tags.

What are the use cases of CassetteAI?

• Game development

  Streaming adaptive background music or generating per-frame sound effects during gameplay using edge inference.
• Real-time media pipelines

  Integrating generated audio into video tools or AR/VR applications requiring low-latency outputs.

How to use CassetteAI?

1. Import the client

   Load the @fal-ai/client package in JavaScript to access the API.
2. Call the endpoint

   Use fal.subscribe() with either CassetteAI/music-generator or cassetteai/sound-effects-generator, passing a text prompt and duration.
3. Retrieve the file

   Access the resulting audio URL from the response object's audio_file property.

CassetteAI Pricing Information:

• Music generation

  $0.02 per output minute; supports durations of 10 to 180 seconds per call.
• Sound effects generation

  $0.01 per generation; supports durations of 1 to 30 seconds per call.
• Text-to-speech

  Pricing to be determined upon launch.

CassetteAI Contact Email:

akhil@cassetteai.com