Cartesia Sonic-3
Cartesia Sonic-3 is a real-time, streaming text-to-speech (TTS) model designed to generate ultra-realistic, expressive voice output with extremely low latency, enabling AI systems to speak as fluidly as humans in live interactions. Built on advanced state space model architecture, Sonic delivers high-quality speech while achieving near-instant response times, with audio generation beginning in as little as 40–100 milliseconds, making conversations feel seamless rather than delayed. It is optimized for conversational AI use cases, acting as the “voice layer” for AI agents by converting text into natural-sounding speech that includes emotional nuance such as excitement, empathy, or even laughter. It supports more than 40 languages with native-level voices and accent localization, allowing developers to build globally accessible applications with consistent quality across regions.
Learn more about Cartesia Sonic-3
Cartesia Sonic-3.6
Sonic is a real-time text-to-speech model built for voice agents, combining natural delivery, sub-90ms latency, and native support for more than 40 languages. It is designed to make voice interactions feel effortless, with tone that adjusts to context, consistent pacing, and speech that follows the natural rhythm of conversation. By default, Sonic interprets the emotional subtext of a transcript and calibrates delivery automatically, while non-verbal expressions such as laughter can be inserted directly into the text. The model follows transcripts faithfully, produces clean audio across languages and voices, and handles alphanumeric content such as order numbers, phone numbers, IDs, and email addresses naturally without preprocessing. Context-aware pronunciation helps heteronyms sound correct from surrounding words, while custom pronunciation dictionaries let teams define how proper nouns and domain-specific terms should be spoken.
Learn more about Cartesia Sonic-3.6
Dessa
Dessa is Block's speech-to-speech artificial intelligence model for conversational voice research and applications. It takes audio input and produces audio output directly, without converting speech into text as an intermediate step. Trained from scratch on human conversation rather than text, the model supports full-duplex interaction, listening and speaking at the same time, and runs locally on a MacBook Pro with an M4 Max chip or better. It captures conversational cues such as emotion, sarcasm, laughter, pauses, and turn-taking that can be lost in text-based pipelines. Dessa is intended for AI safety researchers and developers studying voice-model behavior, privacy, and real-time interaction. It is a speech model for research and development, not a general-purpose business application or hosted voice-agent platform.
Learn more about Dessa
Eleven v4
Eleven v4 is a text-to-speech model from ElevenLabs for generating expressive spoken audio from written scripts. It supports multi-speaker dialogue, emotional direction and audio-event tags, voice cloning, and consistent speaker identity across generated scenes. Creators, publishers, and production teams can use it for narration, audiobooks, character dialogue, video and game voiceovers, and multilingual projects. Developers can generate speech through the ElevenLabs web application or API; the related Eleven v4 Turbo model is intended for real-time speech and voice-agent scenarios. Eleven v4 supports 90+ languages. A free plan includes monthly credits for personal use, while paid plans provide higher credit limits and additional features.
Learn more about Eleven v4