voice agents
11 articles tagged with voice agents
ElevenLabs releases Scribe v3 Live Medical, real-time clinical transcription with 12.8% WER on PriMock57
ElevenLabs has released Scribe v3 Live Medical, a real-time speech-to-text model tuned for clinical language and available now in ElevenAgents. The company claims it posted the lowest WER of the medical models it tested on PriMock57 (12.8%).
Decagon Introduces Alto, a Model That Decides When Its Voice Agent Speaks and What It Says
Decagon introduced Alto on November 11, 2026, a Decagon Labs model that controls the conversational layer of its duplex voice agent. The company reports a resolution rate gain of more than five percentage points on live customer calls, with average responses in about 700 milliseconds.
Fish Audio releases Live 3, a full-duplex voice model that reacts in as little as 186 ms
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. It is English only at launch.
ElevenLabs launches Scribe v3 with 27% fewer word errors across 102 languages, plus realtime Scribe v3 Live
ElevenLabs released Scribe v3 for recorded audio and Scribe v3 Live for realtime audio. The company claims 27% fewer word errors than Scribe v2 across 102 languages for v3, and 43% fewer errors than Scribe v2 Realtime for v3 Live, which also adds speaker diarization for the first time.
ElevenLabs launches ElevenAgents Campaign Manager to run outbound contacts to a defined outcome
ElevenLabs has made ElevenAgents Campaign Manager available now. Given a contact list and a target outcome such as a qualified lead or confirmed appointment, it follows up with each contact over time and carries context between interactions. It works over phone calls, WhatsApp voice and WhatsApp messaging, with email and SMS coming soon.
Soniox releases STT v6, a speech-to-text model that reads a voice agent's text to filter its echo
Soniox has released Soniox STT v6, the latest generation of its speech-to-text API. The model reads what a voice agent says while hearing the caller, and uses that text to recognize short replies and to drop the agent's own voice. It ships as stt-rt-v6 for streaming and stt-async-v6.
AssemblyAI releases AssemblyAI-TTS-1 text-to-speech model at $15 per 1M characters
AssemblyAI has released AssemblyAI-TTS-1, its first text-to-speech model for voice agents. It costs $15 per 1M characters, offers unlimited concurrency without a contract, and supports 6 languages at launch.
Amazon Polly Generative engine upgrade adds 14 voices, first Hindi and Finnish support, at unchanged pricing
AWS has upgraded the Amazon Polly Generative engine in place, adding 14 voices across 9 locales and launching Generative voices in Hindi and Finnish for the first time. The catalog now totals 57 voices across 11 languages and 25 locales. Voice names, API calls, and pricing are unchanged.
Mistral releases Voxtral 3: 50-language transcription, expressive TTS and a real-time voice agent SDK
Mistral AI launched Voxtral 3, a speech family with two transcription models (Voxtral Small Transcribe 3 and Voxtral Mini Transcribe 3), a text-to-speech model (Voxtral Mini TTS 3) and a voice agent SDK. Transcription covers 50 languages, and the 4B-parameter Mini variant costs $0.0035 per minute. It is available through Mistral's EU-hosted API or for self-deployment.
Microsoft's MAI-Transcribe-2-Streaming returns first results in ~100 ms across 60 languages
Microsoft AI released MAI-Transcribe-2-Streaming, a real-time transcription model covering 60 languages with first partial results in just over 100 milliseconds. It also launched two text-to-speech models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash, aimed at voice agents.
AWS launches Nova Sonic voice agent framework with AgentCore Runtime and three integration patterns
AWS released Amazon Nova Sonic, a speech-to-speech foundation model for voice agents, alongside AgentCore Runtime, a serverless hosting environment with WebSocket streaming and microVM isolation. The framework supports three integration patterns: direct tool calls via AgentCore Gateway using Model Context Protocol (MCP), sub-agent delegation with Agent-to-Agent (A2A) protocol, and session segmentation for multi-step workflows.