LiveKit Agents 1.4.0 adds Azure STT TrueText post-processing
STT-only surface for 1.4.0.
Details1 source
livekit-agents 1.4.0 adds a TrueText post-processing option on Azure STT.
livekit-agents 1.4.0
Week 6
2–8 Feb 2026The Hear layer led the week with 4 of 12 filings, from LiveKit, Soniox, Mistral AI and DeepL.
Hearspeech-to-text4
Soniox ships v4 Real-Time STT with semantic endpointing
Streaming sibling to the 29 January v4 Async cut — semantic endpointing and manual finalisation target agent barge-in failures that silence-only VAD still causes.
Details2 sources
Soniox released stt-rt-v4 for low-latency streaming transcription across 60+ languages, with millisecond finality, semantic endpointing, manual finalization, and simultaneous streaming speech translation.
Soniox v4 Real-Time (stt-rt-v4)
Mistral ships Voxtral Transcribe 2 batch and Realtime STT
Open-weight Realtime STT under Apache 2.0 at claimed sub-200ms delay gives voice-agent builders a self-host path alongside a $0.003/min batch API — WER claims are Mistral's benches.
Details1 source
Mistral AI released Voxtral Transcribe 2 as Voxtral Mini Transcribe V2 for batch jobs and Voxtral Realtime for live transcription, with diarization, context biasing, word-level timestamps, and Apache 2.0 open weights for Realtime.
Voxtral Transcribe 2
DeepL Voice API GA for realtime speech transcription and translation
Contact-centre builders get a streamed STT-plus-translation WebSocket on 2 February 2026 — months before DeepL's broader Voice-to-Voice suite in April.
Also Connect
Details2 sources
DeepL opened the DeepL Voice API to API Pro customers so applications can stream audio and receive a source-language transcript plus translations into up to five target languages in real time.
DeepL Voice API
Speaktext-to-speech2
LiveKit Agents 1.4.0 adds Camb.ai TTS plugin
TTS providers clustered into one speak row.
Details1 source
livekit-agents 1.4.0 adds a Camb.ai TTS plugin among speak-path provider work.
livekit-agents 1.4.0
Sarvam releases Bulbul V3 TTS for 11 Indian languages
India-first TTS with 35+ voices and streaming for agents — Josh Talks telephony preference is third-party; full-band still trails ElevenLabs v3 alpha on the same study.
Details2 sources
Sarvam AI released Bulbul V3, a production text-to-speech model with 35+ professional voices across 11 Indian languages, low-latency streaming, consent-based voice cloning, and code-switching for Hinglish and other mixed speech.
Bulbul V3
Showavatars, video1
LiveKit Agents 1.4.0 adds Avatario and Bithuman avatar endpoint options
Avatar plugins filed as one show cluster. Class-2: folded quiet patch(es) 1.4.5 into this row.
Details2 sources
livekit-agents 1.4.0 adds an Avatario avatar plugin and customisable Bithuman GPU avatar endpoint handling.
livekit-agents 1.4.0
ThinkLLMs, speech-to-speech1
LiveKit Agents 1.4.0 adds xAI and Azure OpenAI Responses LLM paths
LLM/Responses cluster separate from orchestration APIs.
Details1 source
livekit-agents 1.4.0 adds xAI Responses LLM and Azure OpenAI Responses integrations.
livekit-agents 1.4.0
Orchestrateframeworks, evals3
LiveKit Agents 1.4.0 (Python + JS) adds LLMStream.collect, tool IDs, and manual realtime turns
Major orchestration API surface for the 1.4 line across Python and Node Agents. Class-2: folded quiet patch(es) 1.4.2, 1.4.5 into this row.
Details4 sources
livekit-agents and @livekit/agents 1.4.0 add LLMStream.collect() for LLM use outside AgentSession, stable tool IDs, commit_user_turn for manual realtime turns, and AgentConfigUpdate with initial judges; the Node package lands on the same 1.4 feature line.
livekit-agents / @livekit/agents 1.4.0
Ada ships Unified Reasoning Engine across Voice, Messaging, and Email
Voice finally shares the same Coaching and Playbooks path as chat and email from early February — one reasoning layer instead of per-channel stacks.
Also UseConnect
Details1 source
Ada began rolling out a Unified Reasoning Engine that replaces channel-specific stacks with one shared intelligence layer across Voice, Messaging, and Email, bringing Coaching and Playbooks onto voice for the first time.
Unified Reasoning Engine
Daily opens aiewf-eval for multi-turn voice-agent LLM testing
Shifts public LLM comparison toward the multi-turn, tool-heavy profile voice agents actually need — and shows accuracy leaders still miss the latency budget that production cascades require.
Details2 sources
Daily released aiewf-eval, an open benchmark that scores text-mode and speech-to-speech LLMs on tool calling, instruction following, knowledge grounding, and latency over ~30-turn voice-agent sessions.
aiewf-eval LLM voice-agent benchmark
Useagents in market1
Epic ships AI Charting ambient note drafting inside Art
Native EHR ambient scribe from Epic itself — raises the bar for third-party ambient vendors that sell into Epic shops.
Also Hear
Details2 sources
Epic released AI Charting, a built-in Art feature that listens during visits, drafts the clinician note, suggests orders from the conversation, and accepts voice commands to reshape note structure.
AI Charting (Art)