# Smallest AI Docs ## Instructions for AI Agents - For clean Markdown of any page, append `.md` to the page URL. - For a complete documentation index, see https://docs.smallest.ai/llms.txt - For section-specific indexes, append `/llms.txt` to any section URL. ## Voice Agents ### Create Agent - [Get Started](https://docs.smallest.ai/voice-agents/platform/create-agent/get-started.md): Create your agent from a template or from scratch. - [Quick start](https://docs.smallest.ai/voice-agents/platform/get-started/quick-start.md): Create and test a working voice agent in 5 minutes, using a template. - [Build your agent](https://docs.smallest.ai/voice-agents/platform/create-agent/build-your-agent.md): The ordered guide to configuring a Smallest AI voice agent: required first, then recommended, then advanced. Ends with publish and activate. - [Overview](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-config.md): Every setting for your agent, in plain terms. - [Prompt](https://docs.smallest.ai/voice-agents/platform/create-agent/prompt.md): Add persona to your agent by writing instructions, role, behavior, and tool calls. - [Speech settings](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/speech-settings.md): Tune how your agent speaks and listens - pacing, background sound, interruptions, and how it handles noisy or unclear audio. - [Tools overview](https://docs.smallest.ai/voice-agents/platform/create-agent/tools-overview.md): Give your agent built-in actions and custom API or client tools it can call mid-conversation. - [Variables](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/variables.md): Dynamic values for personalization and data flow. - [API Calls](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/api-calls.md): Connect agents to external systems. - [Prompt Scoring](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/prompt-scoring.md): Get instant, AI-powered feedback on your agent's system prompt quality. - [Versioning](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/versioning.md): Manage agent config with branches, drafts, and immutable revisions. - [Post call metrics](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/post-call-metrics.md): Extract structured data from every conversation automatically. - [Conversation logs](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/conversation-logs.md): Every call and chat your agent has handled, searchable, filterable, and open for a full replay. - [Widget](https://docs.smallest.ai/voice-agents/platform/create-agent/agent-settings/widget.md): Embed your voice agent directly on your website. - [Concurrency](https://docs.smallest.ai/voice-agents/platform/create-agent/concurrency.md): Control how many simultaneous calls your agents can handle, with an org-wide limit and optional per-agent reservations. - [Knowledge Base](https://docs.smallest.ai/voice-agents/platform/create-agent/knowledge-base.md): Give your agents access to information they can reference during conversations. - [Webhooks](https://docs.smallest.ai/voice-agents/platform/create-agent/developer/webhooks.md): Receive call lifecycle events with full transcripts, metadata, and analytics. - [Integrations](https://docs.smallest.ai/voice-agents/platform/create-agent/developer/integrations.md): Connect your agent to third-party services. - [API Keys](https://docs.smallest.ai/voice-agents/platform/account/api-keys.md): Create, manage, and rotate API keys to authenticate programmatic access to the voice agent platform and Smallest AI models. ### Deploy - [Phone Numbers](https://docs.smallest.ai/voice-agents/platform/deploy/phone-numbers.md): Get and manage phone numbers for your agents. - [Audiences](https://docs.smallest.ai/voice-agents/platform/deploy/audiences.md): Create and manage contact lists for outbound campaigns - [Campaigns](https://docs.smallest.ai/voice-agents/platform/deploy/campaigns.md): Create and manage outbound calling campaigns ### Monitor - [Analytics](https://docs.smallest.ai/voice-agents/platform/monitor/analytics.md): Monitor call performance across your agents and campaigns - [Evaluations](https://docs.smallest.ai/voice-agents/platform/monitor/evaluations.md): Validate your agent before deploying to production. ### Agent SDK - [Embed a voice agent](https://docs.smallest.ai/voice-agents/platform/agent-sdk/embed-a-voice-agent.md): Drop a Smallest Atoms voice agent into a web page, mobile app, or custom client. Integration guides per platform, plus ready-to-fork cookbooks. - [Agent Web SDK](https://docs.smallest.ai/voice-agents/platform/agent-sdk/web-socket-sdk.md): JavaScript SDK for connecting to a Smallest agent from a web page. Handles microphone capture, audio playback, and event streaming over WebSocket. - [Browser Voice Cookbook](https://docs.smallest.ai/voice-agents/platform/agent-sdk/browser-voice-cookbook.md): Connect a browser to an Atoms agent in three steps using the Agent Web SDK. Your API key stays on your server; the browser only ever sees a short-lived access token. - [React Native](https://docs.smallest.ai/voice-agents/platform/agent-sdk/mobile-integrations/react-native.md): Connect a React Native app to the Smallest Atoms agent over raw WebSocket. Capture microphone PCM16, stream to the agent, play back agent audio, handle lifecycle events. - [iOS (Swift)](https://docs.smallest.ai/voice-agents/platform/agent-sdk/mobile-integrations/i-os-swift.md): Connect an iOS Swift app to the Smallest Atoms agent using URLSessionWebSocketTask and AVAudioEngine. Zero third-party dependencies. - [Android (Kotlin)](https://docs.smallest.ai/voice-agents/platform/agent-sdk/mobile-integrations/android-kotlin.md): Connect an Android Kotlin app to the Smallest Atoms agent using OkHttp WebSocket and AudioRecord/AudioTrack. Minimum Android 7 (API 24). - [Flutter](https://docs.smallest.ai/voice-agents/platform/agent-sdk/mobile-integrations/flutter.md): Connect a Flutter app to the Smallest Atoms agent over raw WebSocket. Capture microphone PCM16, stream to the agent, play back agent audio. ### Account - [Subscription & Plans](https://docs.smallest.ai/voice-agents/platform/account/subscription-plans.md): Manage your subscription, compare Pay As You Go vs Enterprise plans, and track credits. - [Organization Members](https://docs.smallest.ai/voice-agents/platform/account/organization-members.md): Manage your workspace, team members, and their roles. ### Cookbooks - [Using Cookbooks](https://docs.smallest.ai/voice-agents/platform/cookbooks/using-cookbooks.md): Code examples, templates, and demos for common voice AI use cases. ### Reference - [Quick Reference](https://docs.smallest.ai/voice-agents/platform/reference/quick-reference.md): Every term, linked to where you need to go. - [Glossary](https://docs.smallest.ai/voice-agents/platform/reference/glossary.md): Definitions of key terms used in Atoms. ### Troubleshooting - [Error reference](https://docs.smallest.ai/voice-agents/platform/troubleshooting/error-reference.md): HTTP status codes returned by the Atoms API and how to recover from each. - [Agent Issues](https://docs.smallest.ai/voice-agents/platform/troubleshooting/common-issues/agent-issues.md): Troubleshoot common problems with voice AI agents. - [Call Quality](https://docs.smallest.ai/voice-agents/platform/troubleshooting/common-issues/call-quality.md): Troubleshoot audio and connection problems. - [Configuration](https://docs.smallest.ai/voice-agents/platform/troubleshooting/common-issues/configuration.md): Troubleshoot setup and settings problems. - [FAQ](https://docs.smallest.ai/voice-agents/platform/troubleshooting/faq.md): Answers to common questions about Atoms. - [Getting Help](https://docs.smallest.ai/voice-agents/platform/troubleshooting/getting-help.md): How to get support when you need it. ### Get Started - [Build with a coding agent](https://docs.smallest.ai/voice-agents/developer-guide/get-started/build-with-a-coding-agent.md): Build voice AI agents with Claude Code, Cursor, or Codex. Paste-ready prompts and MCP for Smallest, plus Lightning TTS and Pulse STT for Pipecat/LiveKit. - [Quickstart Crew CLI](https://docs.smallest.ai/voice-agents/developer-guide/get-started/quickstart.md): Build, test, and deploy agent crews from the terminal. - [Agents CLI](https://docs.smallest.ai/voice-agents/developer-guide/get-started/agents-cli.md): Create, inspect, and place calls from your Atoms agents without leaving the terminal. - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/get-started/overview.md): The Python framework for real-time voice AI agents on Smallest AI. How the pieces fit together, the two versioning axes, and a working end-to-end sample. - [Use Case Finder](https://docs.smallest.ai/voice-agents/developer-guide/get-started/use-case-finder.md): Find the canonical doc for every common voice-agent use case - single-prompt vs crew, phone vs web, knowledge base, tools, deployment, observability. - [Error Handling](https://docs.smallest.ai/voice-agents/developer-guide/get-started/error-handling.md): How exceptions in your crew code surface on the call - auto-emission, severity semantics, graceful fallbacks, and pre-deploy validation. - [Prebuilt tools](https://docs.smallest.ai/voice-agents/developer-guide/get-started/prebuilt-tools.md): Use smallestai.tools to add prebuilt capabilities (web search, and more) to a crew agent in one line. Third-party libraries install as optional extras. - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/get-started/agent-crew-core-concepts/overview.md): The fundamental building blocks of the Atoms Agent Crews SDK - nodes, sessions, events, and graphs. - [Nodes](https://docs.smallest.ai/voice-agents/developer-guide/get-started/agent-crew-core-concepts/nodes.md): The fundamental building blocks of your agent's logic. - [Events](https://docs.smallest.ai/voice-agents/developer-guide/get-started/agent-crew-core-concepts/events.md): The lifeblood of an Atoms application. - [Graphs](https://docs.smallest.ai/voice-agents/developer-guide/get-started/agent-crew-core-concepts/graphs.md): Connect nodes into event processing pipelines. - [Sessions](https://docs.smallest.ai/voice-agents/developer-guide/get-started/agent-crew-core-concepts/sessions.md): The runtime universe for your agent. ### Build - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/overview.md): The brain of your AI application - the multi-node crew that handles conversation. - [Versioning Lifecycle](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/versioning-lifecycle.md): Create, edit, publish, and go live with an agent config through the branch API. Full lifecycle in curl and Python. - [Config Ownership](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/config-ownership.md): What a crew build owns (LLM turn) versus what the platform owns (voice, STT, redaction, first message, timeouts). Change platform settings on the agent config; change crew settings in code and redeploy. - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/llm/overview.md): Setting up the brain of your agent. - [LLM Settings](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/llm/llm-settings.md): Configure models, parameters, and providers. - [Prompts](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/llm/prompts.md): Write prompts that make your voice agent sound natural, stay on track, and get work done. - [BYOM](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/llm/byom.md): Run Atoms agents with your own models. - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/tools/overview.md): Giving your agent the ability to take action. - [Defining Tools](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/tools/defining-tools.md): Create functions that your agent can call. - [Executing Tools](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/tools/executing-tools.md): Register tools and handle LLM tool calls. - [Built-in Tools](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/tools/built-in-tools.md): SDK-provided actions for common tasks. - [Streaming](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/patterns/streaming.md): Stream responses to minimize latency and improve user experience. - [Interruption Handling](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/patterns/interruption-handling.md): Handle user barge-ins gracefully during agent responses. - [State Management](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/patterns/state-management.md): Track and manage data across conversation turns. - [Conversation Flow Design](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/patterns/conversation-flow-design.md): Structure complex conversation paths and branching logic. - [Multi-Agent Orchestration](https://docs.smallest.ai/voice-agents/developer-guide/build/agent-crews/patterns/multi-agent-orchestration.md): Coordinate multiple specialized agents in complex workflows. - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/build/knowledge-base/overview.md): Give your agents accurate, domain-specific knowledge. - [Usage](https://docs.smallest.ai/voice-agents/developer-guide/build/knowledge-base/usage.md): Create, upload content, and connect knowledge bases to your agents. - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/build/calling/overview.md): Make outbound calls with your AI agent. - [Outbound Calls](https://docs.smallest.ai/voice-agents/developer-guide/build/calling/outbound-calls.md): Make phone calls programmatically with your AI agent. - [Call Control](https://docs.smallest.ai/voice-agents/developer-guide/build/calling/call-control.md): End calls and transfer to humans from within your agent. - [Call Transfer](https://docs.smallest.ai/voice-agents/developer-guide/build/calling/call-transfer.md): Transfer a live call to a human or another number, from code - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/build/campaigns/overview.md): Run outbound call campaigns at scale with the Atoms Agent Crews SDK. - [Managing Audiences](https://docs.smallest.ai/voice-agents/developer-guide/build/campaigns/managing-audiences.md): Create and manage contact lists for outbound campaigns. - [Creating Campaigns](https://docs.smallest.ai/voice-agents/developer-guide/build/campaigns/creating-campaigns.md): Create, start, monitor, and manage outbound call campaigns. ### Operate - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/operate/testing-debugging/overview.md): Testing, debugging, and optimizing your agent. - [Logging & Observability](https://docs.smallest.ai/voice-agents/developer-guide/operate/testing-debugging/logging-observability.md): Monitor your agents in development and production. - [Common Issues](https://docs.smallest.ai/voice-agents/developer-guide/operate/testing-debugging/common-issues.md): Troubleshoot frequently encountered problems. - [Overview](https://docs.smallest.ai/voice-agents/developer-guide/operate/analytics/overview.md): Track every call, measure performance, and extract insights. - [Call Metrics](https://docs.smallest.ai/voice-agents/developer-guide/operate/analytics/call-metrics.md): Retrieve call details, transcripts, recordings, and performance data. - [Post-Call Analytics](https://docs.smallest.ai/voice-agents/developer-guide/operate/analytics/post-call-analytics.md): Configure AI summaries and disposition metrics for automated call insights. - [SSE for Live Transcripts](https://docs.smallest.ai/voice-agents/developer-guide/operate/analytics/sse-for-live-transcripts.md): Real-time streaming of user speech (STT) and agent speech (TTS) events for an active call via Server-Sent Events. ### Examples - [Examples](https://docs.smallest.ai/voice-agents/developer-guide/examples/examples.md): Full end-to-end code examples from the cookbook. ### Migrate - [From ElevenLabs](https://docs.smallest.ai/voice-agents/developer-guide/migrate/from-eleven-labs.md): Map ElevenLabs Conversational AI auth, WebSocket protocol, events, and agent creation to Smallest Atoms equivalents. ### Overview - [Deprecation Notices](https://docs.smallest.ai/voice-agents/deprecations/notices.md): Index of Atoms API endpoints that are deprecated or scheduled for removal, with the migration target for each. ### Agent Versioning - [Migration Guide (v1 → v2)](https://docs.smallest.ai/voice-agents/deprecations/agent-versioning-migration.md): Endpoint-by-endpoint mapping from the old /agent/{id}/drafts + /agent/{id}/versions API to the branch-and-revision API. ### Getting Started - [Quick Start](https://docs.smallest.ai/voice-agents/mcp/getting-started/quick-start.md): Connect your AI editor to the Smallest AI platform via the MCP server. Talk to your voice agents, debug calls, transcribe audio, and view analytics from inside Cursor, Claude Desktop, or Claude Code. - [Manual Setup](https://docs.smallest.ai/voice-agents/mcp/getting-started/manual-setup.md): Step-by-step configuration for installing the Smallest MCP server in Cursor, Claude Desktop, and Claude Code. Requires Node.js 18+ and an API key from the Smallest dashboard. ### Using the MCP - [Available Tools](https://docs.smallest.ai/voice-agents/mcp/using-the-mcp/available-tools.md): Reference for all 80 tools the Smallest MCP server exposes. The AI editor picks the right tool from your natural-language prompt - you do not call these directly. - [Prompt Cookbook](https://docs.smallest.ai/voice-agents/mcp/using-the-mcp/prompt-cookbook.md): Copy-paste prompts for every MCP capability - list agents, place outbound calls, transcribe audio, query analytics, manage knowledge bases. Type them in your editor's AI chat in plain English. ### Help - [Troubleshooting](https://docs.smallest.ai/voice-agents/mcp/help/troubleshooting.md): Fix common Smallest MCP setup issues - server not showing up in Cursor or Claude, authentication failures, tool errors, and reload steps for each editor. ### Agent Framework - [LiveKit](https://docs.smallest.ai/voice-agents/integrations/agent-framework/live-kit.md): Build real-time voice agents with LiveKit Agents using Smallest AI TTS and STT. - [Pipecat](https://docs.smallest.ai/voice-agents/integrations/agent-framework/pipecat.md): Build real-time voice AI pipelines using Smallest AI TTS and STT with Pipecat. - [Agno](https://docs.smallest.ai/voice-agents/integrations/agent-framework/agno.md): Give Agno agents a voice with Smallest AI Lightning text-to-speech. - [TEN Framework](https://docs.smallest.ai/voice-agents/integrations/agent-framework/ten-framework.md): Build real-time voice agents on TEN Framework using Smallest AI TTS and STT. ### Agent Platform - [Bolna](https://docs.smallest.ai/voice-agents/integrations/agent-platform/bolna.md): Build voice agents on Bolna using Smallest AI TTS and STT. - [Dograh](https://docs.smallest.ai/voice-agents/integrations/agent-platform/dograh.md): Build voice agents on Dograh using Smallest AI TTS and STT. - [OpenClaw](https://docs.smallest.ai/voice-agents/integrations/agent-platform/open-claw.md): Add ultra-fast TTS and STT to your OpenClaw agent with the Smallest AI skill. - [Rapida](https://docs.smallest.ai/voice-agents/integrations/agent-platform/rapida.md): Build voice agents on Rapida using Smallest AI TTS and STT. - [Speko](https://docs.smallest.ai/voice-agents/integrations/agent-platform/speko.md): Use Smallest AI's Lightning v3.1 and Pulse as the TTS and STT stages in Speko's voice agents. ### Telephony - [Vonage](https://docs.smallest.ai/voice-agents/integrations/telephony/vonage.md): Learn how to integrate Smallest AI TTS in Vonage for telephony solutions. - [Plivo](https://docs.smallest.ai/voice-agents/integrations/telephony/plivo.md): Learn how to integrate Smallest AI TTS in Plivo for telephony solutions. ### SDKs & Libraries - [Vercel AI SDK](https://docs.smallest.ai/voice-agents/integrations/sdks-libraries/vercel-ai-sdk.md): Use Smallest AI TTS and STT with the Vercel AI SDK in Next.js and Node.js apps. - [JellyPod Speech SDK](https://docs.smallest.ai/voice-agents/integrations/sdks-libraries/jelly-pod-speech-sdk.md): Use Smallest AI TTS in any JavaScript or TypeScript app with the JellyPod Speech SDK. ### Automation - [n8n](https://docs.smallest.ai/voice-agents/integrations/automation/n-8-n.md): Automate voice workflows with Smallest AI TTS, STT, and Voice Cloning using the n8n community node. ### Transcription Tools - [OpenWhispr](https://docs.smallest.ai/voice-agents/integrations/transcription-tools/open-whispr.md): Use Smallest AI's Pulse model as the speech-to-text engine inside OpenWhispr, the open-source desktop dictation app. ### AI Gateway - [TrueFoundry AI Gateway](https://docs.smallest.ai/voice-agents/integrations/ai-gateway/true-foundry-ai-gateway.md): TrueFoundry AI Gateway is the proxy layer that sits between your applications and LLM providers, enabling access to 1000+ LLMs with built-in observability and governance. ## Models ### Getting Started - [Models](https://docs.smallest.ai/models/documentation/getting-started/models.md): Find detailed description of each model along with their capabilities and supported languages. ### Text to Speech (Lightning) - [Quickstart](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/quickstart.md): Generate your first speech audio in under 60 seconds with Lightning TTS. - [Overview](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/overview.md): Lightning TTS API - generate speech across 31 languages at 44.1 kHz, ~200ms TTFB, with streaming. Standard 217-voice Lightning v3.1 pool (20 accepted codes, 12 with a trained voice catalog) plus the premium Lightning v3.1 Pro pool covering all 31 languages, plus `auto` cross-language routing. - [Sync & Async](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/sync-async.md): Generate speech synchronously or concurrently - REST API examples. - [Streaming](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/streaming.md): Stream TTS audio in real-time via WebSocket or SSE - first chunk in ~100ms. - [Word Timestamps](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/word-timestamps.md): Per-word timing events interleaved with audio chunks on the Lightning TTS WebSocket - for live captions, karaoke highlighting, and avatar lip-sync. - [Math Notation](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/math-notation.md): Opt-in Lightning TTS flag that reads digit-flanked math operators (x, ×, ÷, spaced -, ^, =) as spoken words instead of leaving them for the number reader. Off by default because dimensions, 24x7, and vehicle-reg codes look like math on paper. - [Pronunciation Dictionaries](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/pronunciation-dictionaries.md): Learn how to create and use pronunciation dictionaries to control how specific words are pronounced in your text-to-speech synthesis - [Voices & Languages](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/voices-languages.md): Find your voice ID, list available voices, filter by language and accent, and find the right voice for your use case. - [HTTP vs Streaming vs WebSockets](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/http-vs-streaming-vs-web-sockets.md): What should you use? - [Performance](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/benchmarks/performance.md): Lightning v3.1 and Lightning v3.1 Pro head-to-head TTS benchmarks: TTFB latency, EmergentTTS naturalness, expressiveness, delivery, accuracy, and MOS quality versus other production TTS systems. - [Metrics Overview](https://docs.smallest.ai/models/documentation/text-to-speech-lightning/benchmarks/metrics-overview.md): Definitions of every Lightning v3.1 TTS quality and latency metric - Naturalness, Expressiveness, Delivery, Accuracy, and MOS variants. ### Speech to Text (Pulse) - [Quickstart](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/quickstart.md): Transcribe your first audio file in under 60 seconds with Pulse Pro. - [Overview](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/overview.md): Smallest Speech-to-Text API. Pulse and Pulse Pro models behind one unified endpoint with multilingual streaming, leaderboard-ranked English accuracy, diarization, word timestamps, and emotion detection. - [Quickstart](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/pre-recorded/quickstart.md): Transcribe pre-recorded audio files using the unified Waves STT endpoint with Pulse or Pulse Pro - [Audio Formats](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/pre-recorded/audio-formats.md): Supported formats, codecs, and recommendations for pre-recorded audio - [Webhooks](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/pre-recorded/webhooks.md): Receive asynchronous Pulse STT results without polling - [Features](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/pre-recorded/features.md): Available features for Pre-Recorded Pulse STT API - [Troubleshooting](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/pre-recorded/troubleshooting.md): Resolve common issues when uploading pre-recorded audio to Pulse STT - [Best Practices](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/pre-recorded/best-practices.md): Prepare audio inputs before submitting them to Pulse STT - [Code Examples](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/pre-recorded/code-examples.md): Complete Python examples for transcribing pre-recorded audio with Pulse Pro and Pulse - [Quickstart](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/realtime-web-socket/quickstart.md): Get started with real-time transcription using the Pulse STT WebSocket API - [Response Format](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/realtime-web-socket/response-format.md): Understanding the structure and fields of real-time transcription responses - [Audio Formats](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/realtime-web-socket/audio-formats.md): Supported audio encoding formats and requirements for real-time WebSocket transcription - [Features](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/realtime-web-socket/features.md): Available features for Real-Time Pulse STT WebSocket API - [Troubleshooting](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/realtime-web-socket/troubleshooting.md): Common issues and solutions for real-time WebSocket transcription - [Best Practices](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/realtime-web-socket/best-practices.md): Optimize your real-time WebSocket transcription for low latency and high accuracy - [Code Examples](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/realtime-web-socket/code-examples.md): Complete code examples for real-time WebSocket transcription in Python, Node.js, and Browser JavaScript - [Word Timestamps](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/word-timestamps.md): Return word-level timing metadata from Pulse STT - [Language Detection](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/language-detection.md): Automatically detect and transcribe across the European, North Indian, South Indian, or East Asian Pulse STT language sets - [Utterances](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/utterances.md): Use the utterances array to capture longer segments with speaker labels - [Diarization](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/diarization.md): Label each word and utterance with turn-by-turn speaker IDs - [Redaction](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/redaction.md): Automatically redact sensitive information from transcriptions - [Gender Detection](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/gender-detection.md): Predict speaker gender alongside every transcription - [Emotion Detection](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/emotion-detection.md): Capture per-emotion confidence scores from Pulse STT responses - [Keyword Boosting](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/keyword-boosting.md): Boost specific words or phrases so the speech-to-text model recognizes them correctly - [Punctuation Formatting](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/punctuation-formatting.md): Control punctuation and capitalization formatting in real-time transcripts - [End-of-Utterance Timeout](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/end-of-utterance-timeout.md): Control how long Pulse waits after speech ends before finalizing the transcript - [Inverse Text Normalization](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/inverse-text-normalization.md): Convert spoken-form transcripts into written form in real time - [Finalize Control](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/finalize-control.md): Take manual control of when transcripts are finalized using `finalize_on_words` and `max_words` - [VAD Events](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/vad-events.md): Acoustic `speech_started` / `speech_ended` events emitted on the Pulse STT WebSocket alongside `transcription` messages when `vad_events=true` is set on the connection. - [Endpointing](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/features/endpointing.md): On-by-default `endpointing` mode on the Pulse STT WebSocket that finalizes transcripts on trailing silence. Set `endpointing=false` to disable. - [Performance](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/benchmarks/performance.md): Pulse and Pulse Pro accuracy and latency benchmarks across FLEURS, ESB, WildASR, and the public Open ASR Leaderboard. - [Metrics Overview](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/benchmarks/metrics-overview.md): Key Pulse STT metrics for quality and latency. - [Evaluation Walkthrough](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/benchmarks/evaluation-walkthrough.md): Step-by-step guide to evaluate Pulse STT accuracy and performance against your own dataset using the Pulse REST API. - [Measuring Latency](https://docs.smallest.ai/models/documentation/speech-to-text-pulse/benchmarks/measuring-latency.md): Measure Pulse streaming + pre-recorded latency using the same metrics the voice-agent industry uses - Time-to-First-Partial, End-of-Turn (EOT), and RTFx - with attribution to the four components of the pipeline. ### Speech to Speech (Hydra) - [Overview](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/overview.md): Hydra is Smallest AI's realtime, full-duplex speech-to-speech model. Audio in, audio out, over a single WebSocket - built for phone-grade voice agents. - [Quickstart](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/quickstart.md): Talk to Hydra in under a minute - a one-clone browser client with multi-agent presets, tool execution, and a live wire log. - [WebSocket connection](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/web-socket-connection.md): Connect to the Hydra speech-to-speech WebSocket - auth, query parameters, idle timeout, close codes. Python, Node, and browser snippets. - [Managing sessions](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/managing-sessions.md): Hydra session lifecycle - session.configure, voices, persona, generate_initial_response, mid-session updates, and conversation items. - [Audio I/O](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/audio-i-o.md): Audio formats for Hydra - input PCM16 16 kHz, output rate negotiation, chunk sizing, and AudioWorklet patterns for browser clients. - [Turn detection & barge-in](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/turn-detection-barge-in.md): How Hydra detects user speech, the events it emits per turn, and how to handle barge-in cleanly on the client. - [Tool calling](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/tool-calling.md): Declare tools in session.configure, stream arguments via response.function_call_arguments, post results back, and let Hydra narrate the answer. - [Prompting voice agents](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/prompting-voice-agents.md): How to write Hydra system prompts that produce natural-sounding voice agents - persona, length discipline, tool-call prompting, and turn-taking. - [Errors & reconnection](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/errors-reconnection.md): Hydra error frame structure, code reference, and reconnection strategy. Errors are diagnostic - the session stays usable unless a close follows. - [Performance](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/benchmarks/performance.md): Hydra head-to-head against eight production realtime voice and speech-to-speech models on the AIEWF S2S benchmark - pass rate and voice-to-voice latency, with and without tool calls. - [Metrics Overview](https://docs.smallest.ai/models/documentation/speech-to-speech-hydra/benchmarks/metrics-overview.md): Definitions of the metrics Hydra is benchmarked on - pass rate, voice-to-voice latency (tool and non-tool), and how each is computed. ### LLM (Electron) - [Quickstart](https://docs.smallest.ai/models/documentation/llm-electron/quickstart.md): Make your first Electron chat completion in under 60 seconds - point the OpenAI SDK at Smallest AI and go. - [Overview](https://docs.smallest.ai/models/documentation/llm-electron/overview.md): Electron - Smallest AI's in-house language model. OpenAI-compatible chat completions, 70 languages with first-class Indic support, voice-agent-optimized tool calling, prefix caching. - [Chat Completions](https://docs.smallest.ai/models/documentation/llm-electron/chat-completions.md): POST /waves/v1/chat/completions - OpenAI-compatible chat completion API. Full request and response reference. - [Streaming](https://docs.smallest.ai/models/documentation/llm-electron/streaming.md): Stream chat completion tokens via Server-Sent Events - the same wire format as OpenAI. Includes optional usage block for accurate billing on disconnects. - [Tool / Function Calling](https://docs.smallest.ai/models/documentation/llm-electron/tool-function-calling.md): Standard OpenAI tools API on Electron, with voice-agent-optimized filler-phrase behavior. Reduces perceived latency on tool calls in conversational pipelines. - [Prefix Caching](https://docs.smallest.ai/models/documentation/llm-electron/prefix-caching.md): Cached input tokens are billed at a discounted rate. Structure your prompts to reuse stable prefixes (system prompts, RAG context, conversation history) and pay less. - [Supported Parameters](https://docs.smallest.ai/models/documentation/llm-electron/supported-parameters.md): What flows through to Electron, what's rejected, and how Electron extends or restricts the OpenAI Chat Completions request body. - [Migrate from OpenAI](https://docs.smallest.ai/models/documentation/llm-electron/migrate-from-open-ai.md): Drop-in replacement for OpenAI's Chat Completions API. Two strings change: the base URL and the API key. - [Best Practices](https://docs.smallest.ai/models/documentation/llm-electron/best-practices.md): How to get the best out of Electron - prompt structure, caching, tool calling, streaming patterns, error handling, and cost control. ### Cookbooks - [Speech to Text](https://docs.smallest.ai/models/documentation/cookbooks/speech-to-text.md): Production-ready code examples for Pulse STT - from real-time streaming to batch transcription. - [Text to Speech](https://docs.smallest.ai/models/documentation/cookbooks/text-to-speech.md): Production-ready code examples for Lightning TTS - from basic synthesis to streaming, voice cloning, and full applications. - [Voice Agent (Electron + Pulse + Lightning)](https://docs.smallest.ai/models/documentation/cookbooks/voice-agent-electron-pulse-lightning.md): Build an end-to-end voice agent on Smallest AI: Pulse for transcription, Electron for the LLM brain (with tool calling), Lightning for speech output. ### Voice Cloning - [Instant Clone (UI)](https://docs.smallest.ai/models/documentation/voice-cloning/instant-clone-ui.md): Clone a voice from a short audio sample using the Smallest AI console. - [Instant Clone (API)](https://docs.smallest.ai/models/documentation/voice-cloning/instant-clone-api.md): Create a voice clone in a single HTTP call using the unified voice cloning API. - [Instant Clone (Python SDK)](https://docs.smallest.ai/models/documentation/voice-cloning/instant-clone-python-sdk.md): Clone a voice from a short audio sample using the Python SDK. ### Best Practices - [Voice Cloning Best Practices](https://docs.smallest.ai/models/documentation/best-practices/voice-cloning-best-practices.md): Guidelines for recording reference audio and achieving high-quality voice clones. - [TTS Best Practices](https://docs.smallest.ai/models/documentation/best-practices/tts-best-practices.md): Voice-agent prompting patterns and text formatting rules that make AI agents sound natural through a text-to-speech engine. ### Troubleshooting - [Error reference](https://docs.smallest.ai/models/documentation/troubleshooting/error-reference.md): HTTP status codes returned by Waves TTS and Pulse STT endpoints, with fixes for each. ### Getting Started - [Introduction](https://docs.smallest.ai/models/self-host/getting-started/introduction.md): Deploy high-performance speech-to-text and text-to-speech models in your own infrastructure - [Prerequisites](https://docs.smallest.ai/models/self-host/getting-started/prerequisites.md): What you need before deploying Smallest Self-Host - [Why Self-Host?](https://docs.smallest.ai/models/self-host/getting-started/why-self-host.md): Understand when self-hosting our models makes sense for your organization - [Architecture](https://docs.smallest.ai/models/self-host/getting-started/architecture.md): Understanding the components and architecture of Smallest Self-Host deployments ### Docker Setup - [Hardware Requirements](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/prerequisites/hardware-requirements.md): Hardware specifications for deploying Speech-to-Text with Docker - [Software Requirements](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/prerequisites/software-requirements.md): Software and dependencies for deploying Speech-to-Text with Docker - [Credentials](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/prerequisites/credentials.md): License keys and registry credentials for STT Docker deployment - [Verification](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/prerequisites/verification.md): Verify all prerequisites before deploying STT with Docker - [Quick Start](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/quick-start.md): Deploy Smallest Self-Host Speech-to-Text with Docker Compose in under 15 minutes - [Cloud Deployment](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/cloud-deployment.md): Recommended GPU instance types on AWS, GCP, and Azure for self-hosting Pulse and Pulse Pro. - [Parallelism and Latency](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/parallelism-latency.md): Throughput, real-time factor (RTFx), and latency figures for self-hosted Pulse and Pulse Pro deployments. - [Services Overview](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/services-overview.md): Detailed breakdown of each service component in the STT Docker deployment - [Configuration](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/configuration.md): Advanced configuration options for STT Docker deployments - [Multi-checkpoint deployment](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/multi-checkpoint-deployment.md): Deploy Pulse STT on-prem with multiple language checkpoints by pairing one API server with one model server, 1:1. Each deployment scales independently. - [Troubleshooting](https://docs.smallest.ai/models/self-host/docker-setup/stt-deployment/troubleshooting.md): Debug common issues and optimize your STT Docker deployment - [Hardware Requirements](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/prerequisites/hardware-requirements.md): Hardware specifications for deploying Text-to-Speech with Docker - [Software Requirements](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/prerequisites/software-requirements.md): Software and dependencies for deploying Text-to-Speech with Docker - [Credentials](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/prerequisites/credentials.md): License keys and registry credentials for TTS Docker deployment - [Verification](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/prerequisites/verification.md): Verify all prerequisites before deploying TTS with Docker - [Quick Start](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/quick-start.md): Deploy Smallest Self-Host Text-to-Speech with Docker Compose in under 15 minutes - [Services Overview](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/services-overview.md): Detailed breakdown of each service component in the TTS Docker deployment - [Configuration](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/configuration.md): Advanced configuration options for TTS Docker deployments - [Troubleshooting](https://docs.smallest.ai/models/self-host/docker-setup/tts-deployment/troubleshooting.md): Debug common issues and optimize your TTS Docker deployment ### Kubernetes Setup - [Hardware Requirements](https://docs.smallest.ai/models/self-host/kubernetes-setup/prerequisites/hardware-requirements.md): Cluster and hardware specifications for Kubernetes STT deployment - [Software Requirements](https://docs.smallest.ai/models/self-host/kubernetes-setup/prerequisites/software-requirements.md): Tools and software for Kubernetes STT deployment - [Credentials](https://docs.smallest.ai/models/self-host/kubernetes-setup/prerequisites/credentials.md): License keys and registry credentials for Kubernetes STT deployment - [Verification](https://docs.smallest.ai/models/self-host/kubernetes-setup/prerequisites/verification.md): Verify all prerequisites before deploying STT on Kubernetes - [Quick Start](https://docs.smallest.ai/models/self-host/kubernetes-setup/quick-start.md): Deploy Smallest Self-Host on Kubernetes with Helm - [EKS Setup](https://docs.smallest.ai/models/self-host/kubernetes-setup/aws/eks-setup.md): Create and configure an EKS cluster for Smallest Self-Host with GPU support - [GPU Nodes](https://docs.smallest.ai/models/self-host/kubernetes-setup/aws/gpu-nodes.md): Advanced GPU node setup and optimization for AWS EKS - [IAM IRSA](https://docs.smallest.ai/models/self-host/kubernetes-setup/aws/iam-irsa.md): Configure IAM Roles for Service Accounts in EKS - [EFS Configuration](https://docs.smallest.ai/models/self-host/kubernetes-setup/storage-pvc/efs-configuration.md): Set up Amazon EFS for shared storage in AWS EKS - [Model Storage](https://docs.smallest.ai/models/self-host/kubernetes-setup/storage-pvc/model-storage.md): Optimize model storage and caching strategies for Lightning ASR - [Redis Persistence](https://docs.smallest.ai/models/self-host/kubernetes-setup/storage-pvc/redis-persistence.md): Configure Redis data persistence and high availability - [HPA Configuration](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/hpa-configuration.md): Configure Horizontal Pod Autoscaling based on custom metrics - [Cluster Autoscaler](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/cluster-autoscaler.md): Automatically scale EKS cluster nodes based on pod resource requirements - [Metrics Setup](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/metrics-setup.md): Configure Prometheus, ServiceMonitor, and custom metrics collection for Lightning ASR - [Grafana Dashboards](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/grafana-dashboards.md): Visualize metrics, autoscaling behavior, and system performance - [Troubleshooting](https://docs.smallest.ai/models/self-host/kubernetes-setup/troubleshooting.md): Debug common issues in Kubernetes deployments ### Troubleshooting - [Common Issues](https://docs.smallest.ai/models/self-host/troubleshooting/common-issues.md): Quick solutions to frequently encountered problems - [Debugging Guide](https://docs.smallest.ai/models/self-host/troubleshooting/debugging-guide.md): Advanced debugging techniques for Smallest Self-Host - [Logs Analysis](https://docs.smallest.ai/models/self-host/troubleshooting/logs-analysis.md): Interpret logs and error messages from Smallest Self-Host ### API Reference - [Authentication](https://docs.smallest.ai/models/self-host/api-reference/authentication.md): Authenticate API requests with your license key - [Health Check](https://docs.smallest.ai/models/self-host/api-reference/endpoints/health-check.md): Monitor service health and availability - [Transcription](https://docs.smallest.ai/models/self-host/api-reference/endpoints/transcription.md): Convert speech to text with the /v1/listen endpoint - [Examples](https://docs.smallest.ai/models/self-host/api-reference/examples.md): Complete examples for integrating with Smallest Self-Host ### Text to Speech - [Lightning v3.1 Pro](https://docs.smallest.ai/models/model-cards/text-to-speech/lightning-v-3-1-pro.md): Model card for Lightning v3.1 Pro. Premium 44.1 kHz TTS pool with a curated voice catalog across American, British, and Indian accents, English + Hindi code-switching, 31 supported languages plus `auto` routing, and improved naturalness. - [Lightning v3.1](https://docs.smallest.ai/models/model-cards/text-to-speech/lightning-v-3-1.md): Model card for Lightning v3.1. High-fidelity, low-latency text-to-speech at 44 kHz with voice cloning, streaming, and 20 supported language codes plus `auto` routing. - [TTS Evaluation Script](https://docs.smallest.ai/models/model-cards/text-to-speech/tts-evaluation-script.md): WebSocket-based evaluation script for measuring Lightning v3.1 TTFB and audio quality. ### Speech to Text - [Pulse Pro](https://docs.smallest.ai/models/model-cards/speech-to-text/pulse-pro.md): Model card for Pulse Pro. High-accuracy English speech-to-text positioned #2 on the public Open ASR Leaderboard. Pre-recorded only, HTTP transport. - [Pulse](https://docs.smallest.ai/models/model-cards/speech-to-text/pulse.md): High-accuracy, low-latency speech-to-text model built for real-time transcription across 31 documented languages (21 streaming + 22 pre-recorded), with regional aggregators and both streaming and non-streaming support. ### LLM - [Electron](https://docs.smallest.ai/models/model-cards/llm/electron.md): Model card for Electron - Smallest AI's in-house language model. OpenAI-compatible chat completions, 70 languages with first-class Indic support, voice-agent-optimized tool calling, prefix caching. ### Speech to Speech - [Hydra](https://docs.smallest.ai/models/model-cards/speech-to-speech/hydra.md): Model card for Hydra - Smallest AI's full-duplex speech-to-speech model. Audio in, audio out, one WebSocket. Built for phone-grade latency and barge-in. ### Client Libraries - [Overview](https://docs.smallest.ai/models/client-libraries/client-libraries/overview.md): Access Client Libraries by Smallest AI. ### Agent Framework - [LiveKit](https://docs.smallest.ai/models/integrations/agent-framework/live-kit.md): Build real-time voice agents with LiveKit Agents using Smallest AI TTS and STT. - [Pipecat](https://docs.smallest.ai/models/integrations/agent-framework/pipecat.md): Build real-time voice AI pipelines using Smallest AI TTS and STT with Pipecat. - [Agno](https://docs.smallest.ai/models/integrations/agent-framework/agno.md): Give Agno agents a voice with Smallest AI Lightning text-to-speech. - [TEN Framework](https://docs.smallest.ai/models/integrations/agent-framework/ten-framework.md): Build real-time voice agents on TEN Framework using Smallest AI TTS and STT. ### Agent Platform - [Bolna](https://docs.smallest.ai/models/integrations/agent-platform/bolna.md): Build voice agents on Bolna using Smallest AI TTS and STT. - [Dograh](https://docs.smallest.ai/models/integrations/agent-platform/dograh.md): Build voice agents on Dograh using Smallest AI TTS and STT. - [OpenClaw](https://docs.smallest.ai/models/integrations/agent-platform/open-claw.md): Add ultra-fast TTS and STT to your OpenClaw agent with the Smallest AI skill. - [Rapida](https://docs.smallest.ai/models/integrations/agent-platform/rapida.md): Build voice agents on Rapida using Smallest AI TTS and STT. - [Speko](https://docs.smallest.ai/models/integrations/agent-platform/speko.md): Use Smallest AI's Lightning v3.1 and Pulse as the TTS and STT stages in Speko's voice agents. ### Telephony - [Vonage](https://docs.smallest.ai/models/integrations/telephony/vonage.md): Learn how to integrate Smallest AI TTS in Vonage for telephony solutions. - [Plivo](https://docs.smallest.ai/models/integrations/telephony/plivo.md): Learn how to integrate Smallest AI TTS in Plivo for telephony solutions. ### SDKs & Libraries - [Vercel AI SDK](https://docs.smallest.ai/models/integrations/sdks-libraries/vercel-ai-sdk.md): Use Smallest AI TTS and STT with the Vercel AI SDK in Next.js and Node.js apps. - [JellyPod Speech SDK](https://docs.smallest.ai/models/integrations/sdks-libraries/jelly-pod-speech-sdk.md): Use Smallest AI TTS in any JavaScript or TypeScript app with the JellyPod Speech SDK. ### Automation - [n8n](https://docs.smallest.ai/models/integrations/automation/n-8-n.md): Automate voice workflows with Smallest AI TTS, STT, and Voice Cloning using the n8n community node. ### Transcription Tools - [OpenWhispr](https://docs.smallest.ai/models/integrations/transcription-tools/open-whispr.md): Use Smallest AI's Pulse model as the speech-to-text engine inside OpenWhispr, the open-source desktop dictation app. ### AI Gateway - [TrueFoundry AI Gateway](https://docs.smallest.ai/models/integrations/ai-gateway/true-foundry-ai-gateway.md): TrueFoundry AI Gateway is the proxy layer that sits between your applications and LLM providers, enabling access to 1000+ LLMs with built-in observability and governance.