One AI provides voice agents for business calls and customer interactions.
Crossing the Uncanny Valley
Sesame’s article discusses conversational voice and the qualities that make spoken interactions feel present.
About Crossing the Uncanny Valley
Crossing the Uncanny Valley of Conversational Voice is a February 2025 research article from AI company Sesame, focused on improving the quality of AI voice interactions. It centers on the concept of "voice presence"—the set of qualities that make spoken exchanges with AI feel genuine, understood, and valuable, rather than flat or impersonal.
The article outlines key components required to achieve voice presence, including emotional intelligence, natural conversational dynamics, contextual awareness, and consistent personality. It also includes an interactive preview of Sesame's conversational speech demo, plus a full technical breakdown of the company's proprietary Conversational Speech Model (CSM), which uses conversation history to generate more natural, context-appropriate speech than traditional text-to-speech systems. The content is intended for people interested in AI voice technology, conversational AI development, and human-computer interaction research.
Key features
- Defines "voice presence" for natural AI spoken interactions
- Offers interactive preview of Sesame's conversational speech demo
- Details technical design of the Conversational Speech Model (CSM)
- Outlines core components for natural AI voice interactions
- Includes full technical research post on conversational speech generation
Best for: This resource is most useful for AI voice researchers, conversational AI developers, and those exploring human-computer voice interaction.
Good for
- Combines conceptual voice UX explanation with technical research details
- Includes interactive demo to preview the technology in action
- Addresses a clear gap in current AI voice assistant design
Watch out for
- The technology is still in development, not a finished product
- The interactive preview is a limited showcase of potential capabilities
- Technical content focuses specifically on Sesame's proprietary CSM approach
Crossing the Uncanny Valley at a glance
- Category
- AI & Machine Learning › AI Voice & Audio
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Crossing the Uncanny Valley alternatives
Tools and sites you could use instead, ranked by how closely they match.
Modulate develops voice AI technology, including an ensemble listening model for interpreting spoken audio.
Convo provides voice-first AI character conversations with real-time audio and video interaction and memory.
Hume provides human ratings and APIs for evaluating voice, speech, and conversational AI.
Popular in AI Voice & Audio
Well-known listings from the same topic.
Google Illuminateilluminate.google.comAlteredaltered.aiELSA Speakelsaspeak.comKreadoAIkreadoai.comPodwisepodwise.aiAddsubtitleaddsubtitle.ai
Crossing the Uncanny Valley FAQ
What is 'voice presence' in AI voice technology?
It is the quality that makes spoken AI interactions feel real, understood, and valuable, per Sesame's research.
What is Sesame's Conversational Speech Model (CSM)?
It is an end-to-end transformer model that uses conversation history to generate more natural, context-aware speech than traditional text-to-speech.
Can I test Sesame's conversational voice technology?
Yes, the page includes an interactive preview of the conversational speech demo for users to try.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.