> ## Documentation Index > Fetch the complete documentation index at: https://slng.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # SLNG: the execution layer for voice > Text-to-speech, speech-to-text, and voice agents through one API. Your orchestrator stays, your models stay. Every turn is routed and optimized for lower cost and lower latency. ● Unmuted # The global execution layer for real-time voice Keep your models. Keep your orchestrator. The execution layer sits between them and cuts cost and latency on every turn. [Install the skills](https://slng.mintlify.site/sdks/skills.md) [Read the quickstart →](https://slng.mintlify.site/getting-started.md) \$ npx skills add slng-ai/skillsTeach your coding agent to build with SLNG, or send your first request by hand. 39%less turn latency, end to end 53%less model cost +16%better call outcomes 30+models behind one API Drop-in ## Plug in the endpoints. Nothing else changes Your orchestrator, your prompts, and your tools stay exactly as they are. Repoint your speech calls at SLNG, and routing, caching, and failover happen behind the endpoint. [How integration works →](https://slng.mintlify.site/integrations/gateway.md) \# keep your orchestrator and prompts. repoint two calls. \- stt: [https://your-current-provider/…](https://your-current-provider/…) \+ stt: [https://api.slng.ai/v1/stt/](https://api.slng.ai/v1/stt/)slng/deepgram/nova:3-enslng/deepgram/nova:3-multisoniox/soniox:latestslng/deepgram/nova:3-en \- tts: [https://your-current-provider/…](https://your-current-provider/…) \+ tts: [https://api.slng.ai/v1/tts/](https://api.slng.ai/v1/tts/)slng/deepgram/aura:2-enslng/rime/arcana:3-enslng/rime/arcana:3-esslng/deepgram/aura:2-en What runs on it ## Three primitives for real-time speech ### [Text-to-Speech](https://slng.mintlify.site/tts/overview.md) Text in, audio out. Multiple voices and languages, over HTTP or streaming WebSocket. ### [Speech-to-Text](https://slng.mintlify.site/stt/overview.md) Transcribe audio files or live streams. Single-language or auto-detect across 10+ languages. ### [Managed Agents](https://slng.mintlify.site/voice-agents.md) An LLM paired with STT and TTS that takes and makes phone calls or runs in the browser. How it works ## Every turn takes the path it actually needs A 16-turn call makes 48 model calls. By default each one runs from scratch, even for a greeting you have synthesized a thousand times. The execution layer changes that across three stages. STAGE 01 ### [STT Performace Layer](https://slng.mintlify.site/execution-layer/stt-performance-layer.md) Route input to the right transcription model, based on language, accent, noise, and use case. STAGE 02 ### [Context Router](https://slng.mintlify.site/execution-layer/context-router.md) Decide whether a turn needs full LLM reasoning, local inference, or no inference at all. STAGE 03 ### [TTS Path Optimization](https://slng.mintlify.site/execution-layer/tts-path-optimization.md) TTS Path optimization relies from cache and synthesis. Don't generate what already exists. ### [Select your region per request](https://slng.mintlify.site/region-override) Pin execution to any of 11 sovereign hubs with a single `X-World-Part` header. Data stays in-jurisdiction. ### [Gets faster with every call](https://slng.mintlify.site/execution-layer/adaptive.md) Each call improves routing decisions and cache coverage for the next. Cost and latency fall as usage grows. Integrations ## Drops into your orchestrator Run SLNG inside the agent framework you already use. Same endpoints, native adapters. ![LiveKit](https://mintcdn.com/slng/LujG4G8gXFrAV3XP/images/providers/livekit.svg?fit=max\&auto=format\&n=LujG4G8gXFrAV3XP\&q=85\&s=5ae1614bbad360d24b36276e04bbc0ea) ### [LiveKit](https://slng.mintlify.site/agents/livekit-plugin.md) Use SLNG models inside LiveKit Agents with the `livekit-plugins-slng` adapter. ![Pipecat](https://mintcdn.com/slng/HUXme6ATYhzzt7mD/images/providers/pipecat.svg?fit=max\&auto=format\&n=HUXme6ATYhzzt7mD\&q=85\&s=f0ff456ad8aa57cfedc6291d915bd330) ### [Pipecat](https://slng.mintlify.site/agents/pipecat-plugin.md) Use SLNG STT and TTS in a Pipecat pipeline with the `pipecat-slng` plugin. [See all integrations →](https://slng.mintlify.site/integrations/overview.md) Bring your own key ## Works with the models you already use Bring your own provider keys and route across 30+ speech models over standard HTTP and WebSocket, without changing your integration. [![Deepgram](https://mintcdn.com/slng/CdBTrLNh-1JX8cv6/images/providers/deepgram.svg?fit=max\&auto=format\&n=CdBTrLNh-1JX8cv6\&q=85\&s=e202d83655428b80684abdf7766a2309)](https://slng.mintlify.site/api-reference/tts/deepgram-aura-2/aura-2-english-ws.md) [![Cartesia](https://mintcdn.com/slng/-M4diEjNjygZHegH/images/providers/cartesia.jpeg?fit=max\&auto=format\&n=-M4diEjNjygZHegH\&q=85\&s=ee4af5467fda6cee5178a34363f496ff)](https://slng.mintlify.site/api-reference/tts/cartesia-sonic-3/cartesia-sonic-3-ws.md) [![Rime](https://mintcdn.com/slng/dfmiEue01ykm71vP/images/providers/rime.png?fit=max\&auto=format\&n=dfmiEue01ykm71vP\&q=85\&s=1d8b09127d77c7790f8a724685b79cb4)](https://slng.mintlify.site/api-reference/tts/rime-arcana-v3/arcana-v3-english-ws.md) [![Murf](https://mintcdn.com/slng/Huk-xqG8QIWj6eh3/images/providers/murf.svg?fit=max\&auto=format\&n=Huk-xqG8QIWj6eh3\&q=85\&s=a3b50a7a1e5c1c4830549ffff031889b)](https://slng.mintlify.site/api-reference/tts/murf-falcon/murf-falcon-ws.md) [![Sarvam](https://mintcdn.com/slng/CdBTrLNh-1JX8cv6/images/providers/sarvam.svg?fit=max\&auto=format\&n=CdBTrLNh-1JX8cv6\&q=85\&s=4ba4b6d4b14f1e4c5771b67361c673df)](https://slng.mintlify.site/api-reference/tts/sarvam-ai-bulbul-v3/bulbul-v3-ws.md) [![Soniox](https://mintcdn.com/slng/dfmiEue01ykm71vP/images/providers/soniox.jpeg?fit=max\&auto=format\&n=dfmiEue01ykm71vP\&q=85\&s=ad6f818b353cfd8f9e2e515617bbdd27)](https://slng.mintlify.site/api-reference/stt/soniox-speech-ai-real-time-v5/speech-ai-real-time-v5-ws.md) ISO 27001 certified. HIPAA and GDPR compliant. [trust.slng.ai](https://trust.slng.ai) [Install the skills](https://slng.mintlify.site/sdks/skills.md) [Read the quickstart](https://slng.mintlify.site/getting-started.md) [Execution layer](https://slng.mintlify.site/execution-layer.md) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.