AI Briefing#voice-agents
The latest AI and developer news about #voice-agents, with the original source and a short summary.
The latest AI and developer news about #voice-agents, with the original source and a short summary.
The partnership includes a sovereign deployment for Poland's e-Health platform and plans to add 15MW of NVIDIA Vera Rubin capacity.
Scribe v3 Live reduces realtime semantic errors by 43% and adds speaker diarization, while Scribe v3 improves batch accuracy in every tested language.
Apache-2.0 model fine-tuned from Qwen2.5-0.5B runs locally on CPU to detect end-of-turn in English and 8 Indic languages.
The SDK connects Unity scenes to ElevenLabs agents via microphone input and AudioSource output, supporting desktop, WebGL, and beta mobile/XR platforms.
The integration allows enterprises to deploy voice agents within existing call flows and routing systems without replacing their current telephony stack.
The guide details how ElevenAgents uses semantic analysis and adaptive timing to manage interruptions and maintain natural dialogue flow.
By deploying ElevenAgents for remote monitoring, Cadence increased patient answer rates from 41% to 60% and enabled immediate nurse escalation for out-of-range vitals.
The new models combine speech recognition, turn-taking, LLM, and voice into a single end-to-end system available via ElevenAgents and an OpenAI-compatible API.
The release includes a LiveKit-based Voice Agent SDK and speech models priced from $0.0035 per minute for transcription and $13 per 1M characters for TTS.
The new Speech to Speech models support 90+ languages and 17,000+ voices, with v1 Max achieving 98.8% accuracy on Big Bench Audio and v1 Mini scoring 75.9%.
Voice Activity Detection (VAD) classifies audio frames as speech or silence in real-time, enabling efficient transcription, telephony, and voice agent interactions.
Beyond the limitations of TF-IDF, dense vector and transformer-based intent recognition technologies enhance the accuracy of LLM agents.
As student AI use surges, education is shifting from one-way content to voice AI conversational learning.
ElevenLabs has renamed Conversational AI to Agents and strengthened its multimodal platform.
It automatically detects voicemail to reduce credits spent on empty calls.