Best Voice agents — Claude

The ranking

1. ★ Editor’s pick

   #1LA

   Leaping AI

   Voice and SMS AI agents for call centres, with built-in telephony, CRM integrations and a no-code agent builder.

   Best forClaude is named as one of the large language models a customer can choose to power an agent; the vendor lists model choice as a platform feature rather than a tier upgrade.

   Claude: Yes — Claude is named as one of the large language models a customer can choose to power an agent; the vendor lists model choice as a platform feature rather than a tier upgrade.“Choice of different Large Language Models (like GPT, Claude, etc.) to power the AI agent.”Pricing page, 'Have full control' feature list, 'Multiple LLMs' row · checked 2026-09-09

   Visit Leaping AI ↗Read the review →Compare Leaping AIGet a quote →From $1,000/month
2. #2TA

   Telnyx Voice AI Agents

   Carrier-owned platform for phone and web voice agents, with telephony, STT, TTS, LLM and orchestration in one stack.

   Best forClaude is selectable as the assistant's model in the Agent tab, and the model table marks a Claude Haiku entry as requiring no API key of your own; prompts still leave Telnyx for Anthropic.

   Claude: Yes — Claude is selectable as the assistant's model in the Agent tab, and the model table marks a Claude Haiku entry as requiring no API key of your own; prompts still leave Telnyx for Anthropic.“Third-party models — including those from Anthropic (Claude), OpenAI (GPT), and Google (Gemini) — are not self-hosted.”STT, TTS, and LLM providers (Voice AI) — Large language model (LLM) · checked 2026-09-09

   Visit Telnyx Voice AI Agents ↗Read the review →Compare Telnyx Voice AI AgentsGet a quote →From $0.05/minute
3. #3VO

   VoiceAgents

   Voice AI platform for phone agents that speak Yoruba, Igbo, Pidgin, Hausa and Nigerian English.

   Best forNigerian SMB and mid-market operators who need a no-code phone agent that handles calls in Yoruba, Igbo, Pidgin, Hausa or Nigerian English out of the box.

   Claude: Yes — Anthropic is one of three selectable LLM providers, chosen per agent.“Mix and match STT, LLM, and TTS providers per agent. OpenAI, Anthropic, ElevenLabs, Deepgram, and more.”Introduction › Key Features, Multi-provider AI card; models listed in Agent Setup › Language Model (LLM) provider table, Anthropic row · checked 2026-09-03

   Visit VoiceAgents ↗Read the review →Compare VoiceAgentsGet a quote →From $15/month

4. Advertisement

   Your agent here. Go Featured to sit above the free listings in this ranking, or buy the slot beside it.

   Get featured · top of your category →
5. #4CA

   Cartesia

   Real-time speech models and a managed runtime for production phone and web voice agents.

   Best forEngineering teams that want an open-source voice-agent SDK with real LLM choice, built on speech models several rival platforms in this category already license as a component.

   Claude: Yes — Anthropic Claude models are named in the SDK's supported-models table and used in its examples.“Anthropic | anthropic/claude-haiku-4-5-20251001, anthropic/claude-sonnet-4-5”LlmAgent > Supported Models table, Anthropic row

   Visit Cartesia ↗Read the review →Compare CartesiaGet a quote →From Free
6. #5DA

   Deepgram Voice Agent API

   One WebSocket API that runs speech-to-text, LLM orchestration and text-to-speech for real-time voice agents.

   Best forEngineering teams that want a managed speech pipeline with real LLM-provider choice, and regulated enterprises that need a self-hosted or VPC deployment option a typical closed-source voice-agent vendor does not offer.

   Claude: Yes — Anthropic is a Deepgram-managed provider, so no endpoint of your own is needed; Claude Sonnet models bill at the Advanced tier and Claude Haiku at Standard.“For open_ai, anthropic, google, and nvidia, the endpoint field is optional because Deepgram provides managed LLMs for these providers.”Supported LLM providers, note under the provider table · checked 2026-09-02

   Visit Deepgram Voice Agent API ↗Read the review →Compare Deepgram Voice Agent APIGet a quote →From $0.05/minute
7. #6PO

   PolyAI

   Enterprise platform for building voice and chat agents that resolve customer calls, priced per minute.

   Best forTeams that want a proven, enterprise-scale, compliance-certified voice AI vendor with a research-led model roadmap, and are prepared to start with a sales conversation: there is no self-serve or free way to trial it today.

   Claude: Yes — Claude is one of the third-party models you can run instead of Raven; the model docs list Claude options under the Amazon Bedrock provider tab, selectable per channel.“If you need to, bring in GPT-5, Claude, Gemini, or others, since no single model fits every enterprise use case, language, or regulatory requirement.”Opening the Agentic Dialog Platform to every builder, 'open to the models you need' paragraph · checked 2026-09-02

   Visit PolyAI ↗Read the review →Compare PolyAIGet a quote →
8. #7LA

   LiveKit Agents

   Open-source Python and Node.js framework for voice AI agents, with LiveKit Cloud hosting, telephony and observability.

   Best forEngineering teams that want to own their voice-agent stack end to end, self-hosted or on LiveKit Cloud, without being locked into one vendor's API.

   Claude: Yes — Anthropic plugin for Python and Node.js, using your own Anthropic API key. Claude is not among the models served through LiveKit Inference, so it is a plugin-only path.“This plugin allows you to use the Claude API as an LLM provider for your voice agents.”Overview, first sentence · checked 2026-09-02

   Visit LiveKit Agents ↗Read the review →Compare LiveKit AgentsGet a quote →From Free
9. #8EA

   ElevenLabs Agents

   Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM.

   Best forDevelopers and product teams who want ElevenLabs' voice quality and cloning as the foundation of their agent, and are comfortable assembling the rest of the stack themselves.

   Claude: Yes — Anthropic models are natively selectable in agent settings; a few older Claude models drop out in EU data-residency workspaces.“for example, OpenAI's GPT-5.6 / GPT-5.5 series, Anthropic's Claude Opus and Claude Sonnet 5, or Google's Gemini Pro models”Choosing a model, Task complexity bullet · checked 2026-09-02

   Visit ElevenLabs Agents ↗Read the review →Compare ElevenLabs AgentsGet a quote →From Free
10. #9RA

    Retell AI

    Pay-as-you-go platform for building, testing and running AI phone, chat and SMS agents.

    Best forProduct and engineering teams that want a low-latency, human-sounding phone agent with flexible model and telephony choice.

    Claude: Yes — Claude models are selectable as the agent's conversation model and priced per minute for voice and per message for chat, alongside GPT and Gemini options.“Claude 5 SonnetRecommended | $0.064/minute”Detailed Component Pricing table, LLM rows · checked 2026-09-23

    Visit Retell AI ↗Read the review →Compare Retell AIGet a quote →From $0.07/minute
11. #10VA

    Vapi

    Developer platform for building, testing and deploying voice AI agents that make and receive phone calls.

    Best forEngineering teams that want maximum control to build custom voice agents on their own choice of model, voice and telephony.

    Claude: Yes — Claude is selectable as the assistant's LLM, on Vapi's integration or your own Anthropic account.“Anthropic builds the Claude family of large language models. On Vapi, you select a Claude model as the LLM for a voice agent.”What is Anthropic section · checked 2026-09-03

    Visit Vapi ↗Read the review →Compare VapiGet a quote →From $0.05/minute