> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.jambonz.org/guides/features/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.jambonz.org/_mcp/server.

# Features

## Docs

- [Voice Agents](https://docs.jambonz.org/guides/features/voice-agents.md): Build conversational AI agents using the [agent](/verbs/verbs/agent) verb.
- [Bring Your Own LLM](https://docs.jambonz.org/guides/features/bring-your-own-llm/overview.md): Configure jambonz to use your own credentials with any of 14 supported LLM providers.
- [Anthropic](https://docs.jambonz.org/guides/features/bring-your-own-llm/anthropic.md): Configure jambonz to use Anthropic's Claude models.
- [AWS Bedrock](https://docs.jambonz.org/guides/features/bring-your-own-llm/aws-bedrock.md): Configure jambonz to use Anthropic Claude, Meta Llama, Mistral, and Amazon Nova models on AWS Bedrock.
- [Azure OpenAI](https://docs.jambonz.org/guides/features/bring-your-own-llm/azure-open-ai.md): Configure jambonz to use OpenAI models hosted in your Azure subscription.
- [Baseten](https://docs.jambonz.org/guides/features/bring-your-own-llm/baseten.md): Configure jambonz to use Baseten's hosted open-weight model catalog or a dedicated Baseten deployment.
- [DeepSeek](https://docs.jambonz.org/guides/features/bring-your-own-llm/deep-seek.md): Configure jambonz to use DeepSeek's V4 family models.
- [Google (AI Studio)](https://docs.jambonz.org/guides/features/bring-your-own-llm/google-ai-studio.md): Configure jambonz to use Google's Gemini models via AI Studio.
- [Groq](https://docs.jambonz.org/guides/features/bring-your-own-llm/groq.md): Configure jambonz to use Llama and Gemma models on Groq's LPU hardware for sub-100ms TTFT.
- [HuggingFace](https://docs.jambonz.org/guides/features/bring-your-own-llm/hugging-face.md): One HuggingFace token, many backends — Groq, Together, Fireworks, Cerebras, Nebius all behind a single broker endpoint.
- [Moonshot (Kimi)](https://docs.jambonz.org/guides/features/bring-your-own-llm/moonshot-kimi.md): Configure jambonz to use Moonshot AI's Kimi models over its OpenAI-compatible API.
- [OpenAI](https://docs.jambonz.org/guides/features/bring-your-own-llm/open-ai.md): Configure jambonz to use OpenAI's chat completions API.
- [Vertex AI — Gemini](https://docs.jambonz.org/guides/features/bring-your-own-llm/vertex-ai-gemini.md): Configure jambonz to use Gemini models via Google Cloud's Vertex AI.
- [Vertex AI — Partner Models](https://docs.jambonz.org/guides/features/bring-your-own-llm/vertex-ai-partner-models.md): Configure jambonz to use Llama, Mistral, and other partner models hosted on Vertex AI's OpenAI-compatible endpoint.
- [Z.ai (GLM)](https://docs.jambonz.org/guides/features/bring-your-own-llm/z-ai-glm.md): Configure jambonz to use Z.ai's GLM models over its OpenAI-compatible API.
- [xAI (Grok)](https://docs.jambonz.org/guides/features/bring-your-own-llm/x-ai-grok.md): Configure jambonz to use xAI's Grok models — reasoning + vision over an OpenAI-compatible API.
- [Using OpenAI STT](https://docs.jambonz.org/guides/features/using-open-ai-stt.md): Taking advantage of OpenAI's prompt feature with jambonz
- [Adding custom speech vendors](https://docs.jambonz.org/guides/features/custom-stt-providers.md): How to add in support for speech vendors that jambonz doesn't natively support
- [Custom TTS providers](https://docs.jambonz.org/guides/features/custom-tts-providers.md)
- [TTS Vendor Settings](https://docs.jambonz.org/guides/features/tts-vendor-settings/overview.md): How to pass vendor-specific tuning to a TTS provider, and which vendors support it.
- [Cartesia](https://docs.jambonz.org/guides/features/tts-vendor-settings/cartesia.md): Speaking rate and emotion controls for Cartesia TTS.
- [ElevenLabs](https://docs.jambonz.org/guides/features/tts-vendor-settings/eleven-labs.md): Voice settings and latency optimisation for ElevenLabs TTS.
- [Gradium](https://docs.jambonz.org/guides/features/tts-vendor-settings/gradium.md): Voice settings and configuration for Gradium TTS.
- [Inworld](https://docs.jambonz.org/guides/features/tts-vendor-settings/inworld.md): Pitch, speaking rate and temperature controls for Inworld TTS.
- [Murf](https://docs.jambonz.org/guides/features/tts-vendor-settings/murf.md): Style, rate, pitch and variation controls for Murf TTS.
- [Resemble](https://docs.jambonz.org/guides/features/tts-vendor-settings/resemble.md): Project selection and HD synthesis for Resemble.ai TTS.
- [Rime Labs](https://docs.jambonz.org/guides/features/tts-vendor-settings/rime-labs.md): Speed, latency and sampling controls for Rime Labs TTS.
- [xAI](https://docs.jambonz.org/guides/features/tts-vendor-settings/x-ai.md): Speed, latency optimisation and text normalization for xAI TTS.
- [Answering machine detection](https://docs.jambonz.org/guides/features/answering-machine-detection.md): Configure answering machine detection in jambonz to identify voicemail and human answers on outbound calls. Tuning parameters explained.
- [Conferencing "coach" mode](https://docs.jambonz.org/guides/features/conferencing-coach-mode.md): Use coach mode in jambonz conferences to whisper to one participant without other callers hearing. Setup and configuration.
- [Continous ASR](https://docs.jambonz.org/guides/features/continous-asr.md): Configure continuous ASR in jambonz to transcribe speech throughout a call instead of in single turns. Setup and tuning parameters.
- [Handling delays in bots](https://docs.jambonz.org/guides/features/handling-action-hook-delays.md): Provide feedback to users while backend processing is happening
- [Managing media anchors](https://docs.jambonz.org/guides/features/managing-media-anchors.md): Control where media anchors in jambonz to reduce latency and meet in-country data requirements. Anchoring options explained.
- [Dual media streams](https://docs.jambonz.org/guides/features/dual-media-streams.md): Configure dual media streams in jambonz to process inbound and outbound audio separately for transcription, recording, or analysis.
- [Call Recording](https://docs.jambonz.org/guides/features/call-recording.md): Enable call recording in jambonz and route audio to your own storage. Configuration options, formats, and compliance considerations.
- [Agent Assist via SIPREC](https://docs.jambonz.org/guides/features/siprec-server.md): Configure a SIPREC server on jambonz for agent assist and call recording. Learn SIPREC session setup, media handling, and requirements.
- [TTS Streaming](https://docs.jambonz.org/guides/features/tts-streaming.md): Cut voice AI latency with TTS streaming in jambonz. Stream synthesized speech as it generates instead of waiting for the full audio file.
- [Using dub tracks](https://docs.jambonz.org/guides/features/dub-tracks.md): Use dub tracks in jambonz to layer additional audio onto a live call for translation, coaching, or background sound. Setup guide.
- [Using Filler Noise](https://docs.jambonz.org/guides/features/filler-noise.md): Add filler noise to jambonz calls to mask processing delays and keep conversations feeling natural. Configuration and audio options.
- [Securing HTTP Endpoints](https://docs.jambonz.org/guides/features/securing-http-endpoints.md): Secure your jambonz HTTP endpoints with webhook signing and authentication so only verified requests reach your application.
- [Webhook and WebSocket retries](https://docs.jambonz.org/guides/features/webhook-and-web-socket-retries.md): Control whether and how many times jambonz retries a failed HTTP webhook or WebSocket connection to your application, using the rc and rp parameters on your application URL.
- [API Rate Limits](https://docs.jambonz.org/guides/features/api-rate-limits.md): Understand jambonz API rate limits, how throttling is applied per account, and how to handle 429 responses in production workloads.
- [Application Environment Variables](https://docs.jambonz.org/guides/features/application-environment-variables.md): Set application environment variables in jambonz to manage credentials, endpoints, and config across deployments without code changes.