Earlybird predicts spoken words before they end in 29M parameters
On LibriSpeech test-clean the median word is correct 90 ms early, and 69% of words are right before they end.
Stories per day · 30 days
1 RSS
Relatedtext-to-speech4mistral3speech-to-text3voxtral3speech-recognition2ai-receptionists1assemblyai1automation1bold-agent-kit1call-centers1codex1contact-center1earlybird1echo-cancellation1employment1latency1librispeech1livekit1
27 stories, newest first · one card per story
Stories tagged #voice-agents
Soniox STT v6 Adds Agent Text Input and Echo Filtering for Voice Agents
Soniox STT v6 introduces agent text input and echo cancellation filtering for voice agents.
AssemblyAI ships TTS-1 API at $15 per 1M characters
The hosted model runs only in US and EU clouds, with six languages, instant cloning and no open weights.
1
VoxLock extracts a target speaker for voice agents without enrollment
On Krisp's 265-recording set it reaches 4.95% WER versus 23.21% unprocessed, with 24 ms latency.
Retell says OpenAI models power more than 100 million monthly calls
Retell reports volume grew from 30 million calls early in 2026, with OpenAI generating responses on 80% of calls.
Mistral AI releases Voxtral 3 speech models and voice SDK
The captured page only preserves the release title; sizes, benchmarks, and availability are not stated.
Mistral launches Voxtral 3 real-time voice agent stack
The stack pairs transcription, speech synthesis and a LiveKit SDK, priced from $0.0035 per minute.
Mistral releases Voxtral 3 speech models and voice agent SDK
The family adds multilingual transcription and speech synthesis, offered on an EU-hosted API or for self-hosting.
Heartbeat Thinking keeps voice-agent tools running while listening
On FDBench v3, tool coverage rises 16 percentage points and mean final-response latency falls 36.4 percent versus a windowed baseline.
Call Center Jobs Are Declining, but 14,000 Calls Show Humans Still Outperform AI
Bold Agent Kit found human receptionists converted inbound calls about four times better than AI across roughly 14,000 calls.
8
Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models
DyaFDB scores both sides of 7,560 full-duplex model conversations instead of using a fixed examiner.
Microsoft AI Releases MAI-Transcribe-2-Streaming: #1 Real-Time Speech-to-Text Model on Artificial Analysis
Microsoft released MAI-Transcribe-2-Streaming, ranking first of 38 models on Artificial Analysis streaming speech-to-text accuracy.
8
Microsoft AI releases new transcription and text-to-speech models for voice agents
Microsoft released MAI-Transcribe-2-Streaming and two MAI-Voice text-to-speech models for low-latency voice agents.
Alibaba Qwen Releases Qwen-Audio-3.1-Realtime: A Full-Duplex Voice Model Trained to Think, Act, and Decide When to Speak
Alibaba released API-only Qwen-Audio-3.1-Realtime, a full-duplex voice model for tool-using agents.
Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents
VGBench shows audio LLMs rarely withhold tool use when a spoken command shifts to a bystander.
Proaction boosts sales 60% and saves 75+ hours with Codex
Fleet software maker Proaction says Codex demos raised deal progression about 60% and saved engineering hours.
Ringg’s AI agents resolve up to 65% of customer calls with OpenAI
Ringg customer-service agents built on OpenAI models resolve up to 65 percent of calls.
MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents
MTVA-Bench evaluates language models inside cascaded voice agents across 490 scenarios and 7 languages, exposing 24.4-point score gaps among seven tested models.
Google Releases Gemini 3.8 Live and 3.8 Live Extended Thinking for Production Grade Voice Agents
Google launches Gemini 3.8 Live and Extended Thinking speech-to-speech models for production voice agents, topping speech-to-speech benchmarks.
Google launches Gemini 3.8 Live to take on OpenAI's GPT-Live-1 at a fraction of the cost
Google DeepMind launches Gemini 3.8 Live speech-to-speech models, topping Artificial Analysis leaderboard at 82.6% with much cheaper pricing than OpenAI.
Gemini 3.8 Live and 3.8 Live Extended Thinking
Google launches Gemini 3.8 Live and 3.8 Live Extended Thinking speech models, topping speech-to-speech benchmarks with parallel reasoning for voice agents.
Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking
Google DeepMind launched Gemini 3.8 Live and 3.8 Live Extended Thinking speech models, topping Artificial Analysis' Speech-to-Speech Quality Index at 82.6.
17
Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents
Duplex Cue evaluation shows PersonaPlex full-duplex agents adapt in-turn to listener contributions in only 34.8% of collaborative cases versus 68.2% for humans.
MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant
MP-Bench is the first benchmark for voice agents in multiparty conversations, finding real-time agents near chance on turn-taking.