ElevenLabs Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs, generating speech in under 75 milliseconds. It supports 32 languages and handles up to 40,000 characters per request, making it ideal for real-time voice agents, conversational AI, and developer applications where response speed is critical. While it trades some expressiveness compared to the Multilingual v2 and v3 models, its speed and efficiency make it the go-to choice for latency-sensitive production deployments.