PulseAugur
EN
LIVE 09:48:20

Fish Audio launches Live 3 full-duplex voice model for agents

By PulseAugur Editorial · [2 sources] ·

Fish Audio has launched Live 3, a full-duplex voice model designed for real-time voice agents. This model can listen and speak simultaneously, allowing for more natural conversational flow by learning turn-taking directly from human interactions rather than relying on predefined pipeline rules. Live 3 is capable of very quick responses, with short acknowledgments like "mm-hmm" starting in as little as 186 milliseconds, and is available via hosted platforms or on-premises deployments. AI

IMPACT Enhances conversational AI agents by enabling more natural, real-time turn-taking and responsiveness.

RANK_REASON Product release of a voice model for agents.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Fish Audio launches Live 3 full-duplex voice model for agents

How we ranked this

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Product release of a voice model for agents.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
product, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [2]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Fish Audio Releases Live 3, a Full-Duplex Voice Model That Reacts in 186 ms

    <p>Fish Audio released Live 3, a full-duplex voice model for voice agents. It listens while it speaks, separates “mm-hmm” from real interruptions, and can react in as little as 186 ms. English only at launch</p> <p>The post <a href="https://www.marktechpost.com/2026/11/10/fish-au…

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Fish Audio has released Live 3, a full-duplex voice model for voice agents that listens while it speaks, learning turn-taking from real conversations rather tha

    Fish Audio has released Live 3, a full-duplex voice model for voice agents that listens while it speaks, learning turn-taking from real conversations rather than pipeline thresholds. It can acknowledge a caller in 186 ms, tell a backchannel from a real interruption and wait out c…

    LINKS marktechpost.com/…/fish-audio-live-3-full…

RELATED ENTITIES

RELATED TOPICS