> ## Documentation Index > Fetch the complete documentation index at: https://docs.slng.ai/llms.txt > Use this file to discover all available pages before exploring further. # Glossary > Definitions of the terms used across the SLNG docs. Short definitions for the terms that appear across these docs. Each term links to the page that covers it in full. ## Products | Term | Definition | | ---------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [**Execution Layer**](/concepts/execution-layer/overview) | The optimisation layer between your orchestrator and the models. It applies caching, routing, and quality features to the Listen, Think, and Speak steps without changing how your agent calls them. | | [**Model Gateway**](/slng-gateway) | One low-latency entry point that routes a speech-to-text or text-to-speech request to the right model in the region you call. | | [**Context Router**](/guides/execution-layer/llm/context-router) | The component in front of the Think step. It decides per turn whether to answer from cache, a small in-region model, a prepared response, or the full model. | | [**Unified API**](/concepts/models/unified-api) | A normalisation layer so every speech provider uses the same request and response shape. Switching providers is a change to the model name, with no other code changes. | | [**Agent Builder**](/concepts/agents/overview) | Where you create, configure, and run voice agents from the dashboard and API. | | [**Unmute**](/unmute) | An open declarative standard for voice agents: describe an agent once, then compile it to a target such as LiveKit, Pipecat, or SLNG. | ## Building blocks | Term | Definition | | ------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [**Project**](/guides/get-started/create-a-project/whats-a-project) | The organizing unit. Everything one voice use case needs (agent, models, keys, tools, telephony, calls) lives inside its project. | | [**Agent**](/concepts/agents/overview) | A voice agent: a configuration that pairs speech-to-text, language, and text-to-speech models with instructions and tools to hold a conversation. | | [**Listen, Think, Speak**](/concepts/execution-layer/overview) | The three steps of a voice agent, mapping to speech to text, the language model, and text to speech. Each is configured and optimised on its own. | | [**Orchestrator**](/concepts/agents/where-they-run) | The software that runs the conversation and glues the models together, either LiveKit or Pipecat. It owns turn-taking and calls the Execution Layer rather than the providers directly. | | [**Pipeline**](/concepts/whats-slng/overview) | The speech-to-text → language model → text-to-speech chain a request passes through on every turn. | ## Capabilities | Term | Definition | | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | | [**Speech to text (STT)**](/concepts/models/speech-to-text) | The Listen step. Turns spoken audio into written text as it happens. | | [**Text to speech (TTS)**](/concepts/models/text-to-speech) | The Speak step. Turns written text into spoken audio. | | [**Large language model (LLM)**](/guides/execution-layer/llm/context-router) | The Think step. Reads the transcript and decides how the agent responds. | | [**ASR**](/concepts/models/speech-to-text) | Automatic speech recognition. Another name for speech to text, used by some providers. | ## Regions and infrastructure | Term | Definition | | ------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | [**Region**](/concepts/whats-slng/regions) | One of the 14 geographic locations a workload runs in. Each region has its own endpoint, and requests are not routed between regions. | | [**In-region execution**](/concepts/execution-layer/where-it-sits) | Running the whole request path close to the caller, in the same region, so no hop is added to a distant location. | | [**Data residency**](/concepts/whats-slng/regions) | Keeping voice data inside a chosen region to meet the rules of a jurisdiction or compliance framework. | | [**PII**](/concepts/whats-slng/regions) | Personally identifiable information. Voice is treated as PII under several compliance frameworks, which is why region and retention are controllable. | ## Models and access | Term | Definition | | --------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [**Provider**](/concepts/models/unified-api) | The vendor of a model, such as Deepgram or Cartesia. A provider can be SLNG-hosted or reached with your own key. | | [**SLNG-hosted vs proxied**](/slng-gateway) | An SLNG-hosted model runs in-region on SLNG infrastructure. A proxied model is an external provider reached through the gateway. | | [**BYOK**](/guides/models/bring-your-own-key) | Bring your own key. Use your own provider keys through SLNG instead of SLNG-hosted models. | | [**Model ID**](/models/catalog/all-models) | The identifier that selects a model, in the form `provider/family:version-lang`. The `slng/` prefix selects an SLNG-hosted, in-region route; a bare `provider/model` is the external or BYOK route. | ## Conversation quality and latency | Term | Definition | | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- | | [**Turn**](/concepts/whats-slng/regions) | One exchange in a conversation: the caller speaks, the agent responds. Turn-taking is real time and has a hard latency budget. | | [**Latency**](/concepts/whats-slng/regions) | The delay before the agent responds. Distance to the region is the largest lever, ahead of any model or pipeline change. | | [**Time to first audio (TTFB)**](/concepts/execution-layer/what-it-optimizes) | How long the caller waits before hearing any audio on a turn. Cached audio removes the synthesis wait. | | [**Word error rate (WER)**](/concepts/execution-layer/what-it-optimizes) | How often the transcription gets a word wrong. Cleaner input audio lowers it, so the model reasons over the right words. | | [**VAD**](/guides/agents/configure/listen) | Voice activity detection. Detects when the caller is speaking, which drives turn-taking. | | [**Endpointing**](/guides/agents/configure/listen) | Deciding when a caller has finished a turn, so the agent can respond without cutting them off. | | [**Diarization**](/concepts/models/speech-to-text) | Separating a transcript by speaker, so it is clear who said what. | | [**Partials vs finals**](/concepts/models/speech-to-text) | In streaming transcription, a partial is an interim result that can still change; a final is the settled text for that segment. | ## Execution Layer optimizations | Term | Definition | | -------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | | [**Noise cancellation**](/guides/execution-layer/stt/noise-cancellation) | Cleans the inbound audio before transcription, which lowers the word error rate. | | [**Pronunciation dictionary**](/guides/execution-layer/tts/pronunciation-dictionaries) | A set of rules for how names, product terms, and domain words are spoken, applied across every text-to-speech provider. | | [**TTS caching**](/guides/execution-layer/tts/tts-caching) | Reuses previously synthesized audio for phrases an agent repeats, cutting cost and time to first audio. | | [**Fallback**](/concepts/execution-layer/what-it-optimizes) | An ordered list of backup models. If a provider fails or times out, the request moves to the next one without your agent handling the retry. | | [**Observation mode**](/concepts/execution-layer/what-it-optimizes) | Points the Context Router at your real traffic without repointing your agent, recording the routing and coverage it would have achieved. | | [**Voice cloning**](/models/catalog/text-to-speech) | Building a custom text-to-speech voice from audio samples, on providers that support it. |