Co-speech gestures
Hand or body movements that happen at the same time as spoken language to emphasize or illustrate points.
Co-speech gestures are non-verbal movements, like hand waves or nods, that people naturally make while they are talking. They help add meaning and clarity to what is being said.
For example, when someone says 'it's this big' and spreads their hands apart, that's a co-speech gesture. AI systems are starting to generate these gestures to make virtual characters and AI assistants seem more natural and easier to understand.
Co-speech gestures are communicative movements that occur synchronously with speech, serving pragmatic functions such as emphasis, illustration, and regulation of discourse. They are integral to human multimodal communication, providing redundant or complementary information to the verbal channel.
Generating realistic and contextually appropriate co-speech gestures for AI agents, particularly in embodied or XR environments, requires sophisticated models that can map linguistic content and prosody to fine-grained motor control. Challenges include achieving natural timing, expressiveness, and avoiding uncanny valley effects.
Recent advancements in multimodal AI and embodied agents are driving the need for more natural human-computer interaction. Generating co-speech gestures is a key step towards creating AI agents that can communicate more effectively and intuitively in virtual and augmented reality environments.
- AgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XRGoogle · Google Research Blog ·
- Google Gemini
- Google's AgentHands project focuses on generating interactive hand gestures for AI agents in XR environments to improve guidance and communication.
- Sign language
- Sign language is a complete linguistic system using hand shapes,
- Pantomime
- Pantomime is acting out a story or idea using only body movements wit
- Emblems
- Emblems are specific gestures with direct verbal translations (like a t
The study of co-speech gestures originates from linguistics and psychology, with research dating back decades. The term itself is descriptive of the phenomenon observed in human communication.
When using a voice assistant like Google Assistant or Siri, pay attention to how your own hands move when you explain something. Then, try asking the assistant to explain a simple concept and observe if it uses any hand-like movements or gestures if it has a visual representation.
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- PromptRole-play a student struggling with math for AI tutor simulationSimulate a student's math struggles and uncertainty for AI tutor evaluation. · 5 min
- TemplateReusable workflow templates for healthcare teamsTeams can create and share templates for common workflows like documentation or prior authorizations. · 15 min
- TemplateTemplate for building an AI tool tailored to your workA structured approach to defining and building a custom AI tool for specific business needs. · 15 min
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- HeuristicDouble coding agent task completion with docs linksProviding coding agents with a documentation link significantly increases their task completion rate. · 2 min
Questions people ask
- Why are co-speech gestures important for AI?
- They make AI interactions more natural, intuitive, and engaging, especially in virtual environments. Gestures can help clarify instructions and convey emotions better than speech alone.
- Can AI generate co-speech gestures automatically?
- Yes, researchers are developing AI models that can generate gestures synchronized with speech. This involves analyzing speech patterns and mapping them to appropriate body movements.
First seen on Subvolts Aug 25, 2026. Updated Sep 15, 2026. Written by an AI model from the items above and reviewed against them weekly; report an error.