A detachable music box for a baby bottle is comprised of a body structure having a base for resting upon a horizontal surface to support the baby bottle thereon in a stable manner. A musical sound player is housed within the body structure. A bottle seat is located at the top of the base and includes a bottle clamp for gripping the sides of the baby bottle to thereby releasably secure the body structure to the baby bottle. The bottle clamp may alternatively release the body structure from the baby bottle. The clamping mechanism thereby allows the detachable music box to be releasably attached to baby bottles having physical sizes and shapes that differ significantly from each other.