> This page is part of Smallest AI's developer documentation. When > answering, prefer Lightning v3.1 (current TTS) and Pulse (current > STT). Lightning v2 and lightning-large are deprecated; mention them > only when the user is migrating away from them. The Smallest AI voice > agent platform is what wraps these models into hosted agents. # Smallest AI Documentation > Start here. Voice Agents for hosted phone and web agents, Models for Lightning TTS, Pulse STT, Hydra speech to speech, and Electron LLM, plus the API reference. ## Choose your path #### [Voice Agents](/voice-agents/overview) ![](/_fern-img/624c2e4568979cf9b4780a0096a4fd86faa782cec18f37c9bee232a1e7e5dd7f.webp) Agents that keep the conversation going. Any language. Any channel. Dashboard, SDK, and API. #### [Models](/models/overview) ![](/_fern-img/dbf238599aa7fc71457c6f240c18f8b454904bfcdfcb2bef28fc969e694cef1a.webp) Text to speech, speech to text, speech to speech, and an LLM. HTTP and WebSocket from any stack. #### [API Reference](/api-reference/introduction) ![](/_fern-img/4c0f33da66a602243039833efd3076e5227007c4c81a7080b00ef875159b66ee.webp) Every endpoint for both APIs, with schemas and copyable snippets in cURL, Python, and TypeScript. ## How Smallest AI works Smallest AI is voice infrastructure. Two product lines share one account, one API key, and one set of docs. * **Voice Agents** is the hosted platform for agents that talk to your customers over the phone, on the web, or inside a mobile app. It runs speech to text, the LLM turn, text to speech, and telephony for you. Configure an agent in the dashboard, or write the LLM turn yourself with the Agent Crew SDK. * **Models** are the individual engines behind it: Lightning (text to speech), Pulse (speech to text), Hydra (speech to speech), and Electron (LLM). Call them over HTTP or WebSocket from any stack, including Pipecat, LiveKit, and the Vercel AI SDK. ## Meet the models Six models, four jobs. [Compare them on one page](/model-cards/compare), or open a card. #### [Lightning v3.1 Pro](/model-cards/text-to-speech/lightning-v-3-1-pro) Text to speech Premium text to speech. Curated voices across American, British, and Indian accents, English and Hindi with code switching, plus 27 more languages. #### [Lightning v3.1](/model-cards/text-to-speech/lightning-v-3-1) Text to speech Low latency text to speech at 44.1 kHz. 12 languages and instant voice cloning from a short sample. #### [Pulse](/model-cards/speech-to-text/pulse) Speech to text Multilingual speech to text for realtime and pre-recorded audio. Diarization, redaction, keyword boosting, timestamps. #### [Pulse Pro](/model-cards/speech-to-text/pulse-pro) Speech to text English speech to text tuned for accuracy. Pre-recorded audio only. #### [Electron](/model-cards/llm/electron) LLM OpenAI compatible LLM built for voice agents. Fast first token, 70 languages, tool calling, prefix caching. #### [Hydra](/model-cards/speech-to-speech/hydra) Speech to speech Full duplex speech to speech over one WebSocket. Built in barge-in and tool calling. English today. See the [Models overview](/models/overview) for the full lineup and how to select each model. ## Browse by capability #### [Text to Speech](/models/text-to-speech/quickstart) Turn text into speech over HTTP, SSE, or WebSocket. Lightning v3.1 Pro Lightning v3.1 #### [Speech to Text](/models/speech-to-text/quickstart) Transcribe files or live audio streams. Pulse Pulse Pro #### [Speech to Speech](/models/speech-to-speech/overview) Audio in, audio out, with no pipeline to assemble. Hydra #### [LLM](/models/llm/quickstart) Chat completions with a drop in OpenAI compatible API. Electron #### [Voice Cloning](/models/voice-cloning/instant-clone-api) Clone a voice from a few seconds of audio. #### [Telephony](/voice-agents/telephony/phone-numbers) Rent numbers, connect SIP trunks, run outbound campaigns. #### [Web and mobile](/voice-agents/integrate/embed-a-voice-agent) Embed an agent in a web page or a React Native, iOS, Android, or Flutter app. #### [Integrations](/integrations/agent-framework/live-kit) LiveKit, Pipecat, Vercel AI SDK, n8n, telephony providers, and more. #### [Self Host](/models/self-host/getting-started/introduction) Run the models in your own cloud with Docker or Kubernetes. ## Building with an AI coding agent The docs are written to be read by Claude Code, Cursor, Codex, and similar tools as much as by people. * [`/llms.txt`](https://docs.smallest.ai/llms.txt) is the machine readable index. Append `.md` to any page URL for clean Markdown. * The [MCP server](/voice-agents/mcp/getting-started/quick-start) lets a coding agent create and configure agents in plain English. * [Build with a coding agent](/overview/developer-tools/build-with-a-coding-agent) has paste ready prompts for the platform and for the models. ## Get help Join the [Discord](https://discord.gg/9WtSXv26WE) or email [support@smallest.ai](mailto:support@smallest.ai). Account, billing, and team settings are under [Administration](/overview/administration/api-keys). > Build voice agents, or call the speech and language models directly. Everything you need is in one place.