Voice Agent APIs
The 9 voice agent platforms in our index that publish a developer-facing API for embedding voice into a third-party product.
On this page
This collection rounds up the voice agent platforms in our index that expose a programmatic integration surface to developers. Each tool here ships with a real interface — a REST endpoint, a WebSocket, an SDK, an MCP server, or an equivalent — so you can wire its voice layer into your own product rather than only use the vendor's hosted console.
Voice-only consumer products, no-API receptionists, and platforms that require a sales call before publishing any integration surface are excluded. The same voice model, behind a real developer API, qualifies; a great voice that ships without one does not.
Why this collection
A tool earns a place here when its own Published, sourced listing names a programmatic integration surface a developer can call: a REST or GraphQL endpoint, a WebSocket, an SDK in at least one general-purpose language, an MCP server, or an equivalent open protocol. The API must be documented and reachable without a sales call — a "contact us" enterprise tier with no self-serve surface named anywhere in the listing does not qualify on its own. Voice-only consumer products that ship without a developer API are out, even where the underlying model is identical. Self-hosted open-source voice frameworks and hosted platforms are both included when each ships an API a developer can call; pricing model, rate limits and self-serve vs. sales-led onboarding vary entry by entry. Membership is re-checked against each listing's own already-researched, gate-passed fields rather than the `voice-agents` and `api` tags in isolation.
9 agents in this collection
Best for Security-conscious enterprises in regulated industries that want a compliant, infrastructure-owned voice platform with deterministic call flows.
Enterprise voice AI that owns its own model stack, priced all-in per minute with no model pass-throughs, and ships a public API for embedding per-minute voice agents into a third-party product.
Best for 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.
The speech-infrastructure vendor's own voice-agent product: a single WebSocket drives managed STT, LLM and TTS, with six named LLM providers and a flat $4.50/hr rate.
Best for 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.
The voice-quality specialist's own agent layer, with a developer API exposing 10,000+ voices, instant cloning, and a bring-your-own-LLM brain behind it.
Best for 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.
OpenAI's own speech-to-speech model API for voice agents, reachable over WebRTC, WebSocket, or native SIP telephony, billed purely on audio tokens with no platform fee.
Best for 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.
The pre-LLM-era enterprise voice AI incumbent ($750M-valued, 200+ enterprise customers), with a published developer surface for embedding its voice agents into a third-party product.
Best for Product and engineering teams that want a low-latency, human-sounding phone agent with flexible model and telephony choice.
Phone-call voice agents built on Retell's turn-taking layer, with a public API to plug in your own LLM, voice, and telephony, shippable over voice, chat or SMS.
Best for 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.
A no-code voice AI platform for enterprise phone agents, with a visual Flow Designer and a developer API exposed alongside the hosted build surface.
Best for 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.
Line, Cartesia's voice-agent SDK, is Apache-2.0 with no caveat; ships as both an open SDK and a published API, the only Apache-licensed open-source voice-agent entry that does so.
Best for 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.
Apache 2.0 voice-agent framework with 13.1k GitHub stars, self-hostable, with a documented API surface and the only open-source voice-agent pick with fully published pricing.
