Fish Audio releases Live 3 full-duplex voice model
The listing cites a 186 ms reaction time, but the fetched page is only a cookie notice.
Stories per day · 30 days
3 RSS
Relatedblock3dessa3speech-model3voice-ai2fish-audio1live-31on-device1speculative-decoding1speech1speech-llm1voice-model1
21 stories, newest first · one card per story
Stories tagged #full-duplex
Speculative Listening speeds speech models using idle compute
It achieves 2.6-2.8x speedup on speak chunks and reduces delay by 73%.
Block unveils Dessa, a full-duplex speech model trained only on speech
The captured page gives no availability, size, languages or benchmark figures beyond the headline.
1
Block releases Dessa, a local full-duplex speech model
Dessa is not publicly available, and Block has asked safety researchers to test it first.
2
Block unveils Dessa, a speech-only model not yet public
It runs locally on a MacBook Pro M4 Max, was trained on one NVIDIA GB200 NVL72, and Block wants security testers.
2
These execs think voice AI hasn’t reached its ChatGPT moment yet
Voice AI execs say the field still lacks a ChatGPT-style breakthrough despite full-duplex models.
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.
HiPLEX: Hierarchical Policy Factorization for Full Duplex Speech Language Models
HiPLEX factorizes full-duplex speech policies so reinforcement learning can improve timing and content separately.
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.
DuplexCadence: Exact State and Execution from a Speech Model's Declared Timelines
DuplexCadence speeds full-duplex speech serving 2.85× and cuts peak memory 38.8% by exposing native clocks.
Tencent's Gander aims to keep talking while it works in the background
Tencent's Hunyuan Speech team introduces Gander, a full-duplex voice model pairing a conversational 'cerebellum' with a swappable background agent 'brain'.
7
NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities
NemotronLabs VoiceChat is an open full-duplex speech-to-speech model that calls tools during real-time conversation.
ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue
ECHO benchmark pairs identical-overlap Chinese dialogue examples with contrasting contexts, revealing most full-duplex systems bias toward yielding the floor.
StepAudio 3 Realtime Technical Report
StepAudio 3 Realtime debuts an audio-language model with Think-While-Speaking reasoning, delivering full-duplex voice dialogue with top benchmark results.
Realtime-Venus: A full-duplex interaction system with asynchronous delegation
Realtime-Venus introduces two 9B full-duplex interaction models (Omni and Audio) that outperform Gemini 3.1 Live and GPT-4o on continuation metrics.
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.
SteerDuplex: Steerable Duplex Speech Dialogue Models
SteerDuplex fine-tunes the Moshi full-duplex speech model with two-stage RL and hybrid rewards to steer tone, persona, and pacing, alongside the new SteerBench benchmark.
OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time
OpenAI's GPT-Live-1 API enables full-duplex speech apps, outperforming GPT-Realtime-2.1 with 0.8s turn-taking latency at $0.05 per minute.
Build more natural voice experiences with GPT‑Live‑1 in the API
OpenAI releases GPT-Live-1 in the API, a full-duplex voice model that handles interruptions natively and delegates reasoning to backend models.
5
Omni Interaction Agent Technical Report
Researchers release Gander, an end-to-end omni interaction model with full-duplex streaming across video, speech, and text plus agentic capabilities.
What Did I Just Say? Self-Listening for Full-Duplex Speech Models
Researchers propose Self-Listening, a full-duplex speech approach feeding realized model speech back as input to improve interruption recovery.