Voice AI Research

Week 2026-W37
11announcements

Daily / Pipecat@pipecat_ai 2 in corpus · first 2026-08-27

2026-09-11 · 2026-W37 · platform · launch · pipecat-ai 1.10.0

Pipecat 1.10.0 adds Meta STT and Speechmatics Agent STT

pipecat-ai 1.10.0 adds MetaSTTService for muse-voice-transcribe-1.0, switches SpeechmaticsSTTService onto Speechmatics Agent STT at /v2/agent with linden-1 as the default model, and removes LmntTTSService after LMNT shut down.

Same week as LiveKit Agents 1.8.1 DuplexModel and OpenAI's 10 Sep GPT-Live-1 API. Pipecat's path is a pipeline service, not LiveKit's DuplexModel class. Filed against the CHANGELOG, not a blog post.

Tavus@tavus 2 in corpus · first 2026-09-10

2026-09-10 · 2026-W37 · model · model · Phoenix-4.5

Tavus Phoenix-4.5 renders full upper-body PALs at 134 ms audio-to-video

Tavus shipped Phoenix-4.5 on 10 Sep: a full-frame generative renderer that moves head, shoulders, posture, and torso with speech, at 134 ms audio-to-video.

Realtime avatar stacks that only animate a face leave body motion static; whole-frame generation plus sub-150 ms A2V is the bar conversational video agents now have to clear.

OpenAI@OpenAI 3 in corpus · first 2026-07-08

2026-09-10 · 2026-W37 · model · api · GPT-Live-1

GPT-Live-1 in the API: full-duplex voice at $0.05/min

OpenAI brought ChatGPT’s full-duplex GPT-Live-1 voice model to the developer API at $0.05/min for the voice layer, with backend models billed separately.

Community cite: ~0.798s turn-taking versus 1.41s for GPT-Realtime-2.1. Backend model billed separately.

LiveKit@livekit 3 in corpus · first 2026-08-12

2026-09-10 · 2026-W37 · platform · launch · livekit-agents 1.8.1 · vendor OpenAI

LiveKit Agents 1.8.1 adds DuplexModel for GPT-Live

livekit-agents 1.8.1 introduces DuplexModel so a session can run a full-duplex speech model, with GPTLiveModel as the first implementation.

SDK counterpart of OpenAI's 10 Sep GPT-Live-1 API. Expressive mode is already filed from the 12 Aug blog; that landed in 1.7.0 on 20 Aug. Do not re-file 1.7.0.

GPT-Live-1 @openaidevs is now supported in LiveKit Agents. It's full-duplex, so it listens and speaks at the same time instead of taking turns, and it hands reasoning and tool calls off to a backend model so a slow lookup doesn't leave your agent sitting in dead air.

https://x.com/livekit/status/2098126102052905001

Hume AI@hume_ai 2 in corpus · first 2026-09-10

2026-09-10 · 2026-W37 · model · other · Voice Replication Leaderboard

Hume publishes a multi-axis voice cloning leaderboard

Hume published a Voice Replication Leaderboard measuring how well 11 TTS models clone 25 reference voices across identity, quality, naturalness, and objective similarity.

Public multi-axis cloning scores rather than one Elo. VoxCPM2 led same-speaker (4.21), Cartesia sonic-3.6-beta led naturalness (4.36), Inworld TTS-2 led quality (4.61).

New from Hume AI: the Voice Replication Leaderboard. Live now on @huggingface, links

https://x.com/hume_ai/status/2098158670131659137

PolyAI@polyaivoice 2 in corpus · first 2026-07-30

2026-09-09 · 2026-W37 · platform · launch · Wren

PolyAI launches Wren, an agent that improves dialog agents from live conversations

PolyAI launched Wren inside Dialog Studio: an agent that reviews every production conversation, proposes fixes and improvements, tests them, and shows metric movement for human approval.

Moves PolyAI from shipping Dialog-RSN-1 models into continuous agent optimisation on live voice and digital traffic, with named customers (Golden Nugget, Hawksmoor, Simplyhealth) already using it.

IDFC FIRST Bank@IDFCFIRSTBank 1 in corpus · first 2026-09-09

2026-09-09 · 2026-W37 · enterprise · partnership · IDFC FIRST Bank × Sarvam AI R&D Lab · vendor Sarvam AI · enabler Sarvam AI

IDFC FIRST Bank and Sarvam open a joint R&D lab for a “self-improving bank”

On 9 Sep, IDFC FIRST Bank and Sarvam AI announced a joint R&D lab aimed at banking AI that learns from operational outcomes, with a post-training factory and regulator-grade safety work.

Indian bank × sovereign AI lab pairing is a concrete enterprise path for continuous post-training under banking controls, not a one-shot model deploy.

HeyGen@HeyGen 1 in corpus · first 2026-09-09

2026-09-09 · 2026-W37 · platform · launch · Professional Voice Clone

HeyGen Professional Voice Clone trains a dedicated voice from 20+ minutes of audio via API

HeyGen opened Professional Voice Clone on the API on 9 Sep: a paid per-slot HeyGen Voice adapter trained on 1–10 recordings totaling at least 20 minutes of one speaker.

Avatar video quality has outrun voice fidelity; a studio-grade clone behind the same API as LiveAvatar closes that gap for builders who already have 20 minutes of clean speaker audio.

Gradium@GradiumAI 2 in corpus · first 2026-07-09

2026-09-09 · 2026-W37 · model · model · Gradium default TTS (perceived TTFA retrain)

Gradium retrains default TTS after Coval starts scoring leading silence in TTFA

After Coval’s June perceived-TTFA change exposed ~225 ms median leading silence in Gradium’s stream, Gradium shipped a new default that emits audible audio in the first 10 ms frame (median TTFA ~214 ms).

Labs that game time-to-first-byte with silent frames get caught when evals score what a caller hears; Gradium’s response shows the metric now steers shipping.

Kissht@Kissht_EMI 1 in corpus · first 2026-09-08

2026-09-08 · 2026-W37 · enterprise · launch · Ring app inbound support (Arrowhead voice agents) · vendor Arrowhead

Kissht’s Ring app: Arrowhead voice agents handle 40% of inbound support

Indian digital lender Kissht was reported to have Arrowhead voice agents handling 40% of inbound customer-support calls on its Ring app, two months after deployment.

A named lender at 40% inbound containment after two months. Arrowhead claims ~88% resolution on those intents; Kissht did not blog it.

AOK PLUS 1 in corpus · first 2026-09-08

2026-09-08 · 2026-W37 · enterprise · launch · Member voice self-service (NiCE Cognigy + CXone) · vendor NiCE

AOK PLUS goes live on NiCE Cognigy and CXone

German public health insurer AOK PLUS went live on NiCE Cognigy and CXone, combining AI voice self-service with member-service operations for more than 5 million annual interactions.

Regulated EU insurer on NiCE’s sovereign cloud. Vendor-stated 5M+ interactions/year, call acceptance above 95%. Announced by NiCE, not AOK PLUS.