> ## Documentation Index > Fetch the complete documentation index at: https://docs.kugelaudio.com/llms.txt > Use this file to discover all available pages before exploring further. # Speech to speech > Give your product a voice agent that hears callers, answers in a natural voice and checks your systems when it needs to, over one WebSocket. Speech to speech runs on Kugel Fluid 1 (`fluid-1`). To see where it sits in your system before you write code, read [Fit it into your stack](/speech-to-speech/integration). ## What you get | Feature | What it does | |---|---| | Audio both ways | PCM16 at 16 or 24 kHz, or G.711 (`audio/pcmu`, `audio/pcma`) at 8 kHz. The agent answers in the format you choose. | | Transcripts | Both sides of the call arrive as text next to the audio. | | Your systems in the call | The agent asks your backend when a turn needs it, and tells the caller the result. | | Interruptions | The caller can talk over the agent, and an event tells you to stop playing audio. | | OpenAI SDK support | The endpoint follows the OpenAI Live API, so the official OpenAI Python SDK works with a KugelAudio key, and [OpenAI's documentation](#use-openais-documentation) answers your questions. You need no KugelAudio SDK. | ## How a call works 1. Your server opens one WebSocket and starts a session with instructions for the agent. 2. You stream the caller's audio in. The agent's voice streams back, with text of both sides. 3. The agent answers what it can from your instructions and the conversation. 4. When a turn needs your systems, the agent tells you. This is a delegation. 5. You do the work and send the result. The agent tells the caller. 6. You close the session, and the event that confirms it reports the seconds used. ## Terms | Term | What it means | |---|---| | **Session** | One conversation on one WebSocket. It lasts at most one hour and is not stored. | | **Agent** | The voice the caller talks to. It listens, decides what to do and speaks. | | **Delegation** | The agent's request for help with one turn. It tells you when a turn needs your systems. | | **Back office** | Whatever does the delegated work: your own backend, or a model KugelAudio runs for you. | | **Commentary** | Facts you send for the agent to tell the caller. | | **Thinking** | Progress you send for the agent to know, without saying it. | | **Instructions** | The agent's brief. You set it at the start and can add to it during the call. | ## Choose who does the work | | [Your backend](/speech-to-speech/your-backend) | [KugelAudio's back office](/speech-to-speech/back-office) | |---|---|---| | `delegation.type` | `client` | `responses` | | Who decides how to do the work | Your code | A model KugelAudio runs | | Who runs your tools | Your code | Your code, when the model asks | | Who writes what the caller hears | The agent, from the facts you send | The model, word for word | | Choose it when | You already have a backend, or your own agent | You want to list your tools and have a model use them | ## Use OpenAI's documentation Speech to speech follows the OpenAI Live API, and you build with OpenAI's own SDK. These pages cover what is KugelAudio's: access, hosts, voices, the back office and limits. For every other question, OpenAI's documentation applies as written: | Question | OpenAI's documentation | |---|---| | Where do I start? | [Getting started with GPT-Live](https://developers.openai.com/api/docs/guides/live) | | How do I connect, start and close a session, and which audio formats are there? | [WebSockets](https://developers.openai.com/api/docs/guides/voice-websockets?api=live) | | Which events carry audio and transcripts, and how do I mute or add earlier conversation? | [Managing sessions](https://developers.openai.com/api/docs/guides/live-conversations) | | How do delegation, commentary, thinking and tools work? | [Delegation and tools](https://developers.openai.com/api/docs/guides/live-delegation) | | How do I call it from Python? | [OpenAI Python SDK](https://github.com/openai/openai-python) | Where KugelAudio differs, [Coming from OpenAI Live](/speech-to-speech/openai-compatibility) lists it. Everything not listed there works as OpenAI describes. ## Prerequisites - **An API key allowed Realtime sessions.** In the dashboard this is **Realtime sessions** set to **Allowed** (`realtime:write`), or an unrestricted key. See [key permissions](/api-reference/authentication#key-permissions). ## Choose a host Set the SDK's `base_url` to one of these, with `/v1` at the end. The SDK opens `/v1/live/sessions` on it. | Host | `base_url` | |---|---| | Default | `https://api.kugelaudio.com/v1` | | EU | `https://api.eu.kugelaudio.com/v1` | | US | `https://api.us.kugelaudio.com/v1` | Send the key as the dashboard shows it. The `eu-` key prefix belongs to the KugelAudio SDKs, so a prefixed key fails here. ## Next steps See the setup for a phone line, a web page or LiveKit Talk to it from your microphone in a few minutes Handle interruptions, pick a voice, mute and restart Look up every event, field, error and close code