AI Briefing#voice-agent
The latest AI and developer news about #voice-agent, with the original source and a short summary.
The latest AI and developer news about #voice-agent, with the original source and a short summary.
A new benchmark and dataset have been released to evaluate speech recognition performance on code-switching speech that mixes multiple languages.
ServiceNow has released EVA-Bench 2.0, a dataset for evaluating voice AI agents that includes 3 enterprise domains.
Hugging Face has released a guide for building a local voice agent using the Reachy Mini robot.
A real-time TTS and voice cloning model supporting sub-60ms low latency and self-hosting has been released.
This introduces how to build an ElevenAgents voice agent in half a day using Claude Code and connect it to an actual phone call.
Mahindra automated XUV 7XO launch consultations with an ElevenLabs-powered AI voice agent.
AssemblyAI has launched an API for voice agents.
ElevenLabs has added pre-configured agent templates to ElevenAgents.
For Somali TTS, XTTS V4 works best so far, but the LLM and Whisper layers remain bottlenecks.
Nana cut customer support costs by 85% and reduced response times to seconds by adopting AI agents.
Building a successful voice agent requires more than simple responses—it demands system control privileges and stable governance.
Compares the characteristics and trade-offs of Cascaded and Fused architectures for building voice agents.
This introduces how to implement a Santa voice agent in a React app using ElevenLabs' Agents Platform and React SDK.
For voice agents to perform sensitive tasks, deterministic tool-based authentication design—rather than LLM judgment—is essential.
This presents strategies for effectively managing enterprise internal knowledge and leveraging RAG and context injection methods to improve the accuracy of voice agents.
ElevenLabs has introduced self-hosted LLMs into its agent platform, reducing latency and improving cost efficiency for voice agents.
ElevenLabs has unveiled **Scribe V2 Realtime**, a real-time transcription model with ultra-low latency performance under 150ms.
Burda has partnered with ElevenLabs to integrate enterprise audio and voice agent solutions into its AI platform AISSIST.
ElevenLabs is hosting an online conversational agent hackathon together with its partners.
ElevenLabs unveiled Conversational AI 2.0, featuring RAG integration and natural conversational flow.
ElevenLabs has launched an official MCP server that lets LLMs control voice agents and audio features.
In 2025, Conversational AI is expected to evolve into proactive voice agents equipped with emotional intelligence and real-time translation.
ElevenLabs has cut the per-call cost of its Conversational AI service by up to 50%.
A practical build and optimization advice for creating an offline companion robot with an 8GB ThinkPad was shared.