Ranked · Voice agents
The Best AI Voice Agents (2026)
11 AI voice agent tools — OpenAI Realtime API, Deepgram Voice Agent API, Cartesia, Vapi, Retell AI, Bland AI, ElevenLabs Conversational AI, LiveKit Agents, PolyAI, Synthflow AI and SkipCalls — compared on what actually differs: how much of the stack you own vs. assemble yourself, whether you can self-host it, who can actually operate it (developer vs. no-code), the real per-minute cost once every billed component is added up, and how much enterprise track record backs the vendor.
The ranking
14 agents, compared. Start with fit and price, then open the full assessment. Payment does not alter this ranking. Selection and method ↓
All picks at a glance
Compare fit and price, then choose a name to read the full assessment.
| # | Agent | Best for | From |
|---|---|---|---|
| 1 | OpenAI Realtime APIThe raw model itself, no platform at all | Engineering teams building a voice agent from scratch who want to go directly to OpenAI's own speech-to-speech model (no orchestration platform, no per-minute markup) and are comfortable being single-vendor on OpenAI. | Usage-based |
| 2 | Deepgram Voice Agent APIThe speech-infra company's own stack, deployable anywhere | Engineering 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. | $4.50 |
| 3 | CartesiaThe other speech-infra company's stack — open-source SDK, 100+ LLMs | Engineering 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. | Free |
| 4 | VapiMaximum flexibility, bring-your-ownvs Retell AI | Engineering teams that want maximum control to build custom voice agents on their own choice of model, voice and telephony. | On quote |
| 5 | Retell AIVoice-quality and low-latency leadervs Vapi | Product and engineering teams that want a low-latency, human-sounding phone agent with flexible model and telephony choice. | On quote |
| 6 | BlandAll-in pricing, owned infrastructure | Security-conscious enterprises in regulated industries that want a compliant, infrastructure-owned voice platform with deterministic call flows. | On quote |
| 7 | ElevenLabs AgentsThe voice-quality specialist's own agent layer | Developers 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. | Free |
| 8 | SynthflowNo-code, ops-team-first | Operations and CX teams at mid-market or enterprise companies who want a visual, no-code way to design and launch phone agents without an engineering ticket. | Subscription |
| 9 | LiveKit AgentsOpen infrastructure, self-hostedvs PolyAI | Engineering 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. | Free |
| 10 | PolyAIEnterprise-proven, sales-ledvs LiveKit Agents | Teams 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. | On quote |
| 11 | SkipCallsA packaged receptionist, nothing to assemble | $19.99/mo | |
| 12 | Auto-RespondIn this category, not yet ranked | Local service business owners who lose leads to slow follow-up and want phone and marketplace messages answered and booked automatically on their own calendar. | $99/mo |
| 13 | VoiceAgentsIn this category, not yet ranked | Nigerian 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. | $12.50/mo |
| 14 | AudioCodes Live HubIn this category, not yet ranked | On quote |
Selection, context, and ranking method
AI voice-agent products are not interchangeable. The first three entries are the underlying building blocks: OpenAI Realtime API is the raw model, Deepgram Voice Agent API is speech infrastructure with managed, VPC-hosted and self-hosted deployment, and Cartesia combines its Sonic and Ink models with an Apache 2.0 Line SDK. They suit teams that want to assemble the system themselves. Vapi, Retell AI and Bland AI are the next tier of developer-facing platforms: Vapi maximizes provider control, Retell emphasizes turn-taking and voice quality, and Bland AI publishes the clearest all-in hosted rate.
The bill is a second ordering principle because “per minute” does not mean the same thing across this set. OpenAI is token-metered and Deepgram is connection-time metered, with additional options depending on the components supplied. Cartesia separates agent minutes from monthly speech-model credits and telephony. Vapi and Retell separate orchestration from model, voice and telephony costs; ElevenLabs uses a subscription minute pool plus overage and can bill an external LLM and telephony separately. Synthflow AI currently has no public pricing anchor, while LiveKit Agents is free up to 1,000 agent-session minutes but still leaves inference and provider spending outside that allowance. PolyAI remains sales-led with no public rate card, and SkipCalls is a flat subscription whose own site and App Store listings currently show different prices. Bland AI is the clearest published all-in entry rate, although its higher tiers add platform fees.
The useful choice is therefore fit, not one universal winner. Start with OpenAI for lowest-level model control, Deepgram for speech infrastructure and deployment flexibility, or Cartesia for an open SDK. Choose Vapi or Retell for a custom build, Bland for a predictable hosted bill, ElevenLabs for voice quality and variety, Synthflow for a no-code ops path, LiveKit for self-hosting, PolyAI for established enterprise deployments, or SkipCalls when a finished receptionist is more useful than infrastructure. The list is intentionally ordered from the rawest building block to the most packaged product; it is not claiming that a model, an API, a no-code platform and a receptionist are direct substitutes. Every entry is a Published listing, and the notes below use the current pricing and capability anchors rather than treating a headline rate as a complete bill.
Ranked by the buying job each product serves, from the raw speech model to the finished receptionist—not by a single universal quality score. The first group covers model and speech infrastructure, followed by developer platforms, an all-in hosted option, a voice specialist, a no-code path, an open-source framework, an enterprise incumbent and a packaged receptionist. Within the page’s progression, a position reflects the combination of capability transparency, deployment control, published cost and audience fit; a lower headline price never wins when mandatory components are omitted, and no-code or enterprise suitability can justify a lower position. Every entry is a Published listing with a distinct voice-agent role; general agent builders that merely expose a voice channel are not treated as equivalent products. Reordering follows the current pricing and deployment facts in each listing, while every note calls out a meaningful limitation rather than treating a feature list as a verdict.
The ranking
The raw model itself, no platform at all
Editor’s pick
#1
OpenAI Realtime API
OpenAI's speech-to-speech API for low-latency voice agents over WebRTC, WebSocket or SIP.
Best forEngineering teams building a voice agent from scratch who want to go directly to OpenAI's own speech-to-speech model (no orchestration platform, no per-minute markup) and are comfortable being single-vendor on OpenAI.
Ranked first as the raw model, not a platform: gpt-realtime-2.1 bills $32/$64 per 1M audio tokens in/out (the mini is about one-third), with no platform fee or bundled telephony. WebRTC, WebSocket and native SIP are available, but session management, tool calling and observability remain the builder’s job; the listing estimates $0.06–$0.11/min with cache-friendly usage.
The speech-infra company's own stack, deployable anywhere
- #2
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.
Second for teams that need speech infrastructure and deployment control in one API. The current Standard tier is $4.50/hour, while pay-as-you-go spans $0.050–$0.163/min depending on which STT, TTS and LLM you bring or buy; managed, VPC and self-hosted deployment, SOC 2 Type II, HIPAA BAAs and a one-time $200 credit distinguish it. It still lacks the dashboard, CRM integrations and permanent free tier of a full platform.
Visit Deepgram Voice Agent API ↗Read the review →Get a quote →from $4.50/hr Standard / Standard to Custom (BYO LLM and TTS) The other speech-infra company's stack — open-source SDK, 100+ LLMs
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.
Third for speech-model quality plus an open agent SDK. Sonic and Ink are the product foundation, while Line connects to 100+ LLMs; pricing is deliberately two-meter: $0.06/min agent time plus a separate $0.014/min Cartesia phone number and monthly Sonic/Ink credits. The SDK is Apache 2.0, but the deployed Line runtime is not self-hostable, and the current free tier is $0/month with 20K credits and a $1 agent balance.
Maximum flexibility, bring-your-own
- #4
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.
Fourth for developer control: choose the speech-to-text, LLM and text-to-speech providers, then use Vapi to orchestrate calls. The current pricing anchor starts at $0.05/min for the Build orchestration fee, with model, voice and telephony pass-throughs kept separate. That flexibility is valuable for custom stacks, but it demands engineering and a complete budget for every component; there is no turnkey no-code route.
Voice-quality and low-latency leader
- #5
Retell AI
Platform for building, testing and deploying AI voice and chat agents on phone, web and SMS, billed per minute.
Best forProduct and engineering teams that want a low-latency, human-sounding phone agent with flexible model and telephony choice.
Fifth for teams prioritizing turn-taking, call flow and QA around a developer-built stack. Pay-as-you-go starts at $0.07/min, and the listing’s basic-build example is about $0.11/min after its voice infrastructure, TTS, telephony and LLM components. It is easier to operate than a bare API, but the bill still depends on the selected stack and engineering remains useful for production quality.
All-in pricing, owned infrastructure
Best forSecurity-conscious enterprises in regulated industries that want a compliant, infrastructure-owned voice platform with deterministic call flows.
Sixth for a predictable hosted bill. Bland owns the model stack and publishes $0.14/min with no platform fee on the entry tier; Build and Scale trade lower per-minute rates for $299/month and $499/month platform fees. That is the clearest all-in option in this set, with the tradeoff of enterprise-oriented packaging and less freedom to swap individual models, voices or telephony providers.
The voice-quality specialist's own agent layer
- #7
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.
Seventh when voice quality and voice variety matter more than minimizing the number of vendors. The agent layer uses 10,000+ voices and supports 70+ languages, with a $0/month plan and paid plans from $6 to $990/month; overage starts at $0.08/min ($0.16 in burst), while the LLM and external telephony can bill separately. It is a strong voice specialist, not a turnkey CRM-operations platform.
No-code, ops-team-first
- #8
Synthflow
Enterprise voice AI platform with in-house telephony for inbound and outbound call automation.
Best forOperations and CX teams at mid-market or enterprise companies who want a visual, no-code way to design and launch phone agents without an engineering ticket.
Eighth for ops or CX teams that want a visual Flow Designer instead of hand-written orchestration. The current listing has no published pricing anchor, so treat the cost as a quote rather than comparing a per-minute headline: it is aimed at enterprise phone agents, offers a structured Build-Evaluate-Launch-Learn method and publishes OpenAI as the available LLM choice. It is the no-code path, but the missing price anchor makes budgeting less transparent.
Open infrastructure, self-hosted
- #9
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.
Ninth for teams willing to own the code and deployment. LiveKit Agents is Apache 2.0, self-hostable and the only open-source framework in this set; the current listing says $0/month with 1,000 agent-session minutes, and its production positioning includes powering OpenAI’s ChatGPT Advanced Voice Mode. The free allowance is small, so meaningful usage still requires your own providers or LiveKit’s metered inference.
Enterprise-proven, sales-led
- #10
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.
Tenth for large enterprises that value deployment history over self-serve economics. Founded in 2017, PolyAI is sales-led again after its brief self-serve tier disappeared; the current listing publishes no rate card, while third-party estimates put typical contracts around $150,000/year. Its differentiator is the established enterprise track record and multilingual deployment base, not transparent pricing or hands-on access.
A packaged receptionist, nothing to assemble
- #11
SkipCalls
AI phone receptionist that answers, screens and books calls for small service businesses.
Eleventh for a small business that wants a finished receptionist rather than infrastructure. SkipCalls answers missed calls, filters spam and books appointments on an existing number, with a flat subscription and trial; the listing records a current discrepancy between $19.99/month on its site and $29.99/month in the App Store. Growth and Enterprise tiers needed for webhooks, email receptionist or unlimited agents have no published price, and the listing does not state a STIR/SHAKEN attestation level.
In this category, not yet ranked
- #12
Auto-Respond
AI voice and messaging agent that answers calls and marketplace leads, qualifies them, and books jobs.
Best forLocal service business owners who lose leads to slow follow-up and want phone and marketplace messages answered and booked automatically on their own calendar.
- #13
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.
- #14
AudioCodes Live Hub
Self-service SaaS for building voice AI agents and connecting them to SIP trunks, Teams, WhatsApp and WebRTC.
Side by side
Scroll across to compare every product. Feature names stay in view.
| Feature | OpenAI Realtime API | Deepgram Voice Agent API | Cartesia | Vapi | Retell AI | Bland | ElevenLabs Agents | Synthflow | LiveKit Agents | PolyAI | SkipCalls | Auto-Respond | VoiceAgents | AudioCodes Live Hub |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Description | OpenAI's speech-to-speech API for low-latency voice agents over WebRTC, WebSocket or SIP. | One WebSocket API that runs speech-to-text, LLM orchestration and text-to-speech for real-time voice agents. | Real-time speech models and a managed runtime for production phone and web voice agents. | Developer platform for building, testing and deploying voice AI agents that make and receive phone calls. | Platform for building, testing and deploying AI voice and chat agents on phone, web and SMS, billed per minute. | Enterprise voice AI platform for phone agents, running its own self-hosted models. | Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM. | Enterprise voice AI platform with in-house telephony for inbound and outbound call automation. | Open-source Python and Node.js framework for voice AI agents, with LiveKit Cloud hosting, telephony and observability. | Enterprise platform for building voice and chat agents that resolve customer calls, priced per minute. | AI phone receptionist that answers, screens and books calls for small service businesses. | AI voice and messaging agent that answers calls and marketplace leads, qualifies them, and books jobs. | Voice AI platform for phone agents that speak Yoruba, Igbo, Pidgin, Hausa and Nigerian English. | Self-service SaaS for building voice AI agents and connecting them to SIP trunks, Teams, WhatsApp and WebRTC. |
| Category | Voice agents | Voice agents | Voice agents | Voice agents | Voice agents | Voice agents | Voice agents, Agent platforms | Voice agents | Voice agents, Agent frameworks | Voice agents | Voice agents | Support agents, Voice agents | Voice agents | Voice agents |
| Pricing | $32 / $64 audio / per 1M tokens | $4.50/hr Standard / Standard to Custom (BYO LLM and TTS) | $0 / month | $0.05 / min | $0.07–$0.31 / min | $0.14/min / minute | $0 / mo | $0.11-$0.16 / min | $0 / month | Custom (per minute, sales-led) | $19.99/mo | $99/month | $12.50/month | Paid |
| Tags |
Get quotes from the top agents
Describe what you need. We route it to the best-matched providers.
Frequently asked questions
- What is the best AI voice agent platform?
- There is no universal winner. OpenAI Realtime API is the raw speech-to-speech model for teams that want full control. Deepgram Voice Agent API combines speech infrastructure with managed, VPC and self-hosted deployment. Cartesia pairs Sonic/Ink speech models with an Apache 2.0 Line SDK. Vapi and Retell AI are developer-facing platforms, while Bland AI is the clearest published all-in rate. ElevenLabs prioritizes voice quality and variety, Synthflow AI is the visual no-code path, LiveKit Agents is the open self-hostable framework, PolyAI is the enterprise incumbent, and SkipCalls is a packaged receptionist.
- Which AI voice agent platform has true all-inclusive pricing?
- Bland AI is the clearest published all-in option: its entry rate is $0.14/min with no platform fee, while Build and Scale publish $0.12/min plus $299/month and $0.11/min plus $499/month platform fees. OpenAI is token-metered rather than per-minute; Deepgram is connection-time metered; Cartesia separates agent minutes from speech-model credits and telephony. Vapi, Retell AI and ElevenLabs expose component costs, LiveKit leaves inference spending outside its free allowance, and PolyAI has no public rate card.
- How much do AI voice agent platforms actually cost per minute?
- OpenAI Realtime API is usage-based: the current listing shows $32/$64 per 1M audio tokens in/out for gpt-realtime-2.1 and about one-third of that on the mini, with an estimated $0.06–$0.11/min under cache-friendly production usage. Deepgram lists $4.50/hour Standard time and $0.050–$0.163/min pay-as-you-go depending on the components supplied. Cartesia lists $0.06/min for agent time, $0.014/min for a Cartesia phone number and separate monthly model credits. Vapi starts at a $0.05/min Build orchestration fee; Retell starts at $0.07/min and gives an approximately $0.11/min basic-build example; Bland publishes $0.11–$0.14/min before its tier platform fees; ElevenLabs starts with a $0/month plan and charges overage from $0.08/min; Synthflow currently has no public pricing anchor; LiveKit includes 1,000 agent-session minutes at $0/month but usage beyond that is separate; PolyAI is custom; and SkipCalls is a flat subscription with conflicting public prices.
- Which of these eleven owns its own infrastructure end to end?
- They divide into several models. OpenAI Realtime API is the model itself, with no platform layer around it. Deepgram Voice Agent API can run managed, VPC-hosted or fully self-hosted. Cartesia owns its Sonic/Ink speech models, but its Line agent runtime is managed. LiveKit Agents is open-source and fully self-hostable. Bland AI and PolyAI run their own hosted stacks, while Vapi, Retell AI, ElevenLabs and Synthflow AI are bring-your-own-provider to some degree. SkipCalls is a finished receptionist rather than an infrastructure stack.
- Which is cheapest to start using?
- Vapi has the lowest published orchestration number at $0.05/min, but it excludes model, voice and telephony. LiveKit Agents has the most usable long-term free allowance at 1,000 agent-session minutes/month, while OpenAI and Deepgram have no dedicated ongoing free tier and PolyAI is sales-led. ElevenLabs has a $0/month plan with 15 call minutes, and Cartesia has a $0/month plan with 20K model credits and a $1 agent balance. Headline price is not the same as the complete bill for most entries.
- Is there an open-source alternative to these hosted platforms?
- Yes, but the shape differs. LiveKit Agents is the only genuinely open-source, self-hostable framework in this set and removes platform lock-in at the cost of writing and deploying the code yourself. Cartesia’s Line SDK is Apache 2.0, but the Line runtime and the Sonic/Ink models are not self-hostable in the same way. Deepgram offers managed, VPC-hosted and self-hosted deployment of its closed-source engine. OpenAI is a closed model API, so its openness is provider choice and direct access rather than self-hosting.
- Which of these eleven is built for regulated industries like healthcare or finance?
- Bland AI, Deepgram, PolyAI, Cartesia and Synthflow AI are the most direct regulated-industry candidates. Bland publishes an all-in per-minute entry rate and enterprise deployment options; Deepgram offers managed, VPC and self-hosted deployment with SOC 2 Type II and HIPAA BAAs; Cartesia publishes enterprise compliance and BAA options; PolyAI has the longest enterprise track record but is sales-led; Synthflow targets enterprise phone agents with visual operations tooling. LiveKit is a strong choice when a team wants self-hosting and accepts responsibility for its own compliance program, while OpenAI is a lower-level API rather than a turnkey regulated-industry product.
- Which of these eleven has the deepest enterprise track record?
- PolyAI, by a clear margin. Founded in 2017, it is the oldest name in the set and has the deepest established enterprise deployment history, including a large multilingual customer base; its current listing remains sales-led and publishes no rate card. That track record comes with an access tradeoff: buyers must enter a custom enterprise engagement, and the current third-party contract estimate is around $150,000/year rather than a self-serve price.
Advertise here
Reach buyers mid-decision. Reach builders choosing their next agent. Promote your brand with a display placement or bring your listing into focus with Featured.
Explore owner options →Advertise on this page →The digestFree
Which agents actually ship.
What we re-checked, what got added, and one number from the index. Tuesdays.
One-click unsubscribe