Agent Switchboard

Stacks

A realtime voice agent

The four parts of an agent you talk to: a realtime framework, speech recognition, a fast model and a voice.

4 tools · API · CLI

In this stack · 4

  1. LiveKit Agents

    API · CLI

    Builds production realtime voice and video AI agents with WebRTC transport, turn detection, and STT/LLM/TTS pipelines.…

    VerifiedOfficialby LiveKit · Voice & Messaging · 3 skills · API Key

    Why Runs the conversation: streams audio over WebRTC, detects when the speaker is done, and chains speech-to-text, the model and text-to-speech.

  2. Deepgram

    API · CLI

    Speech-to-text and voice AI API with real-time streaming transcription, speaker diarization, and text-to-speech for…

    VerifiedOfficialby Deepgram · Voice & Messaging · API Key

    Why Hears the user, with real-time streaming transcription and speaker diarization.

  3. Cerebras Inference

    API

    Serves open-weight LLMs such as Qwen and GPT OSS through an OpenAI-compatible API on wafer-scale hardware, for…

    VerifiedOfficialNewby Cerebras · Language & Translation, Infrastructure & Ops · 4 skills · API Key

    Why Thinks fast: serves open-weight models such as Qwen and GPT OSS through an OpenAI-compatible API, built for very fast inference.

  4. Cartesia

    API

    Delivers ultra-low-latency text-to-speech and speech-to-text through the Sonic model family, with a voice-agent…

    Verifiedby Cartesia · Voice & Messaging · 3 skills · API Key

    Why Answers out loud with low-latency text-to-speech, in a custom voice cloned from a short sample.

/stacks/realtime-voice-agent
4 tools · access api+cli · in order
The four parts of an agent you talk to: a realtime framework, speech recognition, a fast model and a voice.
in this stack
livekit-agentsapi+cliRuns the conversation: streams audio over WebRTC, detects when the speaker is done, and chains speech-to-text, the model and text-to-speech.deepgramapi+cliHears the user, with real-time streaming transcription and speaker diarization.cerebras-inferenceapiThinks fast: serves open-weight models such as Qwen and GPT OSS through an OpenAI-compatible API, built for very fast inference.cartesiaapiAnswers out loud with low-latency text-to-speech, in a custom voice cloned from a short sample.
more
/stacksevery stack/api/stacks/realtime-voice-agentthis stack as JSONGET · no auth