Talk & Listen (Voice)

Real-time omni-model handling text, vision and voice in a single network.

High-fidelity video generation with native synchronised audio.

Open multilingual speech recognition and translation model.

Best-in-class expressive TTS and voice cloning across 70+ languages.

Generates full songs with vocals from a text prompt.

Text-to-music model focused on production-quality tracks.

Source-grounded research assistant with audio overviews.

OpenAI text-to-speech voices via the audio API.

Google's professional music generation model.

High-fidelity expressive TTS voices on Google Cloud.

Multilingual speech-to-speech and speech-to-text translation.

Open text-to-music model from AudioCraft.

AI avatar video generator for marketing and training.

Ultra-low-latency state-space TTS model.

Conversational TTS optimised for AI agents.

Voice cloning and real-time speech synthesis platform.

Production-grade streaming speech-to-text model.

Highly accurate speech recognition with rich audio intelligence.

Open ASR model optimised for real-time edge inference.

Generates full-length audio tracks from text.

AI music generation with vocal & instrumental control.

AI-powered language tutoring features.

Pixel SoC powering on-device Gemini Nano features.

Suite of on-device + cloud AI features for Galaxy phones (translate, edit, summarize).

Voice-first in-car AI assistant integrating Alexa LLM features.

Pocket AI device built around the Large Action Model paradigm.

Smart glasses with multimodal Meta AI for live look-and-ask.

AI for evidence redaction, transcription and investigations for law enforcement.

AI-powered software-defined vehicle OS with voice and personalization.

AI assistant for meeting summaries, chat and email across Zoom.

GenAI assistant for meetings, contact center and collaboration.

Voice-enabled clinical documentation agent for clinicians.

GenAI for contact-center agents, self-service and analytics.

HIPAA-eligible service that generates clinical notes from patient conversations.

Generative contact-center AI for virtual agents, agent assist and insights.

Revenue AI for call insights, forecasting and deal execution.

GenAI and predictive AI across Twilio messaging, voice and Segment.

AutoQA AI that scores 100% of support conversations across voice and chat.

Speech-to-text, summaries and language operators that analyze every call in real time.

Build conversational AI agents over SMS, voice and WhatsApp grounded in Segment data.

Ambient AI scribe for clinicians that drafts notes and orders from doctor-patient conversations.

Personalized AI DJ that curates and narrates listening sessions in a realistic voice.

We introduce Reka Core, Flash, and Edge, a series of powerful multimodal language models trained from scratch by Reka.

We’re announcing GPT-4o, our new flagship model that can reason across audio, vision, and text in real time.

We’re announcing GPT-4o, our new flagship model that can reason across audio, vision, and text in real time.

Fugatto is a versatile audio synthesis and transformation model capable of following free-form text instructions with optional audio inputs.

Today, we’re releasing an experimental version of Gemini 2.0 Pro that responds to that feedback.

We’re announcing GPT-4o, our new flagship model that can reason across audio, vision, and text in real time.

Gemini 2.5 Pro Experimental is our most advanced model for complex tasks.

We’re announcing GPT-4o, our new flagship model that can reason across audio, vision, and text in real time.

Gemini 2.5 Pro Experimental is our most advanced model for complex tasks.

Gemini 2.5 Pro Experimental is our most advanced model for complex tasks.

To advance Gemini’s capabilities towards solving hard reasoning problems, we developed a novel reasoning approach, called Deep Think, that naturally blends in parallel thinking techniques during response generation.

We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts.

Our most capable vision-language model (VLM) reasons about the physical world, natively calls digital tools and creates detailed, multi-step plans to complete a mission.

ByteDance's image generation, video, audio model tracked by Epoch, focused on video generation.

Google DeepMind's audio model tracked by Epoch, focused on audio generation.

Empathic voice interface that perceives and generates emotional speech in real time.

Inflection's empathetic conversational assistant tuned for personal, supportive dialogue.

Stability AI's 2B text-to-audio diffusion model for higher-capacity music, sound-effect generation, and audio editing.

Alibaba's vision-enhanced real-time audio/video translation model for live multilingual interpretation across 60 languages.

Mirelo's text-to-sound-effects model for production-ready Foley, ambience, and SFX generation.

Meta's audio generation model focused on high-fidelity waveform synthesis and speech-music co-generation.

Resemble AI's expressive multi-character voice acting model for long-form dramatic dialogue and narration.

Stability AI's compact text-to-sound-effects diffusion model optimized for low-latency on-device SFX generation.

Stability AI's compact text-to-music diffusion model tuned for short, license-friendly musical loops and stems.