Voice agents hold real-time spoken conversations — answering calls, qualifying leads, and handling support with sub-second latency. The category covers full phone-agent platforms and the speech infrastructure underneath them.
Production RAG platform with reasoning, hybrid search, and full multimodal support.
Google Cloud streaming and batch speech recognition API v2 with improved accuracy, streaming, and noise suppression for real-time agent pipelines.
Framework for building real-time, multimodal AI agents with voice, video, and data channels.
Enterprise speech and conversational AI platform for clinical and contact-center workflows with HIPAA-capable deployments.
Production-grade voice AI framework with sub-250ms latency, WebRTC support, multimodal (voice+vision+text), real-time streaming, and 70+ language support.
Enterprise voice AI platform for natural multi-turn conversations with high-volume call handling.
Open-source conversational AI framework with self-hosted NLU training and dialogue management.
Voice orchestration platform for multimodal AI agents with 50+ language support, workflow building, and enterprise integrations.
AgentIndexed currently lists 8 voice agents, including Agentset, Google Cloud Speech-to-Text v2, LiveKit Agents, Nuance AI and more. Featured placements appear first, then all tools alphabetically.
Test latency and interruption handling first — they make or break the experience Check telephony integrations (SIP, Twilio) for call-center use Evaluate voice quality and language coverage for your market.
Submit it free on the submit page (reviewed in 5–7 days), or go Featured for $49 to be reviewed within 24 hours and placed at the top of this category.
Featured agents appear first in this category and on the homepage. One-time $49, live within 24 hours.
Get featured →