> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.rubrichq.io/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.rubrichq.io/_mcp/server. # Daily Connect your own voice bot — built with [Pipecat](https://docs.pipecat.ai) or anything that can join a [Daily](https://docs.daily.co) room — and let RubricHQ's simulated caller talk to it over real audio. Both parties join **one Daily room**: * **`rubric-test-caller`** — RubricHQ's AI caller, running your scenario. * **your agent-under-test** — the bot you're testing. They publish and subscribe to each other's audio; RubricHQ records the call and produces transcript + audio metrics. > **Tip** > > Prefer LiveKit as your transport? The model is identical — see [LiveKit](/integrations/livekit). --- ## The model: rooms, tokens, and who creates them A few Daily facts that decide how the integration is wired: * A **room** (a `https://.daily.co/` URL) is one call/session. A **meeting token** authorizes one identity to join one room. * **Creating rooms and minting meeting tokens requires your Daily API key.** **Joining a room requires only the room URL + a meeting token** — never the API key. * So the only real question is **who creates the room and mints the tokens.** That gives two modes: | Mode | Room management | Who creates the room + mints tokens | Whose Daily key | What you implement | | -------------------- | --------------- | ----------------------------------- | -------------------------- | ----------------------------------------------------------------------- | | **You create rooms** | `client` | **You** | Yours (stays on your side) | An endpoint that creates a room and returns a join token for our caller | | **We create rooms** | `rubric` | **RubricHQ** | Yours, stored in RubricHQ | An endpoint that **joins** a room we created | Configure this under **Agent → Channels → Web**, provider **Daily**. > **Note** > > Credentials are **only needed for "We create rooms"** mode — that's where *we* create the room and mint tokens. In "You create rooms" mode we never see your API key; you hand us a scoped meeting token. --- ## Credentials (for "We create rooms") Provide your Daily **API key** in either place — RubricHQ resolves **per-agent override → workspace default → error**: 1. **Workspace default** — **Settings → Integrations → Transport Providers → Daily**: `API Key`. Used by every agent that doesn't override. 2. **Per-agent override** — **Agent → Channels → Web → "We create rooms" → Daily API key**. Overrides the workspace default for that one agent. > **Tip** > > The API key is write-only: once saved it shows **"Configuration saved"** and is never sent back to the browser. Leave it untouched to keep it; click **Edit** to replace it. --- ## Mode 1 — You create rooms (`client`) You own the Daily account; RubricHQ never needs your key. **Config** | Field | Value | | --------------- | ---------------------------------------------------------------------------- | | Room management | `You create rooms` (`client`) | | Bot Runner URL | Your endpoint, e.g. `https://your-bot.example.com/api/create-and-join-daily` | **Sequence** 1. RubricHQ POSTs to your **Bot Runner URL** with the run context. 2. Your service **creates a Daily room**, starts your bot in it, and **returns a meeting token** for our caller. 3. RubricHQ's caller joins that room with the `room_url` + `token` you returned, and the conversation runs. **What we send → your Bot Runner URL** ```json POST {bot_runner_url} Content-Type: application/json { "rubric_run_id": "1234", "metadata": { "scenario_id": 8, "scenario_name": "Cooperative Upbeat Payment Flow", "agent_id": 1 } } ``` **What you return (immediately, in the HTTP response)** ```json { "room_url": "https://your-domain.daily.co/client-459ff0f5", "token": "" } ``` > **Note** > > The room + token come back **in the HTTP response** — not via a webhook. By the time you respond `200`, the room must exist and the token must be valid, because RubricHQ's caller joins immediately. **Reference bot runner (`client` mode)** ```python # POST /api/create-and-join-daily import secrets, time, httpx DAILY = "https://api.daily.co/v1" H = {"Authorization": f"Bearer {DAILY_API_KEY}", "Content-Type": "application/json"} async def create_and_join_daily(req): room_name = f"client-{secrets.token_hex(4)}" exp = int(time.time()) + 3600 async with httpx.AsyncClient(timeout=15) as c: r = await c.post(f"{DAILY}/rooms", headers=H, json={ "name": room_name, "privacy": "private", "properties": {"exp": exp, "max_participants": 10}, }) room_url = r.json()["url"] async def mint(user): t = await c.post(f"{DAILY}/meeting-tokens", headers=H, json={ "properties": {"room_name": room_name, "user_name": user, "exp": exp}}) return t.json()["token"] bot_token, caller_token = await mint("pipecat-bot"), await mint("rubric-test-caller") start_your_bot_in(room_url, bot_token) # your agent joins return {"room_url": room_url, "token": caller_token} ``` --- ## Mode 2 — We create rooms (`rubric`) RubricHQ creates the Daily room with your API key, mints a token for your bot and one for our caller, then POSTs your join endpoint so your bot enters the room. **Config** | Field | Value | | ----------------------------- | --------------------------------------------------------------------------------- | | Room management | `We create rooms` (`rubric`) | | Web Call URL / Bot Runner URL | Your join endpoint, e.g. `https://your-bot.example.com` (we call `…/api/session`) | | Daily API key | per-agent or workspace | **Sequence** 1. RubricHQ creates a Daily room and mints a `bot_token` (for your bot) and a caller token (for our caller). 2. RubricHQ POSTs your join endpoint with the `room_url` and the `bot_token`. 3. Your bot joins that room with the token we minted; our caller joins too; the conversation runs. **What we send → your join endpoint** ```json POST {web_call_url}/api/session Content-Type: application/json { "room_url": "https://your-domain.daily.co/rubric-188-aaa02027", "token": "" } ``` **What you return** ```json { "status": "started", "room_name": "https://your-domain.daily.co/rubric-188-aaa02027" } ``` > **Note** > > Your bot doesn't need its own Daily key here — it joins **our** room with the **token we minted**. It only needs the `room_url` and `token` from the request. **Reference bot runner (`rubric` mode — Pipecat)** ```python # POST /api/session — join a Daily room RubricHQ already created async def create_session(req): start_your_bot(room_url=req["room_url"], token=req["token"]) return {"status": "started", "room_name": req["room_url"]} ``` --- ## Optional room config — "Room Properties (JSON)" When **RubricHQ creates the room** ("We create rooms"), you can pass any Daily room [`properties`](https://docs.daily.co/reference/rest-api/rooms/config) as JSON under **Agent → Channels → Web → Room Properties (JSON)**. They're merged into the room's `properties`; RubricHQ's required keys (`exp`, `max_participants`) take precedence. ```json { "enable_recording": "cloud", "enable_dialout": false, "lang": "en", "start_audio_off": false, "eject_at_room_exp": true } ``` ### Recording `enable_recording` controls Daily-side recording. Allowed values: | Value | Result | | -------------------- | -------------------------------------------------------------------------------------------- | | `"cloud"` | Daily records to its cloud (composite). Requires a Daily plan that includes cloud recording. | | `"cloud-audio-only"` | Audio-only cloud recording. | | `"raw-tracks"` | Per-participant raw track recordings. | | `"local"` | Client-side local recording. | | *(omit)* | No Daily-side recording. | When Daily-side cloud recording is enabled, RubricHQ also fetches the **vendor's own recording link** after the call and surfaces it on the run, alongside our capture. > **Note** > > Whatever you set here, RubricHQ always captures its **own speaker-separated recording** of the call for analysis, so transcript and audio metrics work even if you leave Daily-side recording off. This JSON is for *your* room preferences (keeping a vendor-side copy, language, timeouts, etc.). ### Commonly useful properties | Key | Type | Description | | ---------------------------------- | ------------- | ------------------------------------------------------------ | | `enable_recording` | string | Daily-side recording mode (see above). | | `max_participants` | int | Max simultaneous participants (RubricHQ sets a default). | | `exp` / `nbf` | int (unix ts) | Room expiry / not-before (RubricHQ sets `exp`). | | `eject_at_room_exp` | bool | Eject everyone when the room expires. | | `eject_after_elapsed` | int (sec) | Eject a participant N seconds after they join. | | `lang` | string | Prebuilt UI language (`en`, `es`, `fr`, `de`, …, or `user`). | | `geo` | string | Preferred server region for signaling/media. | | `start_audio_off` | bool | Join with mic muted. | | `start_video_off` | bool | Join with camera off. | | `enable_chat` | bool | Enable in-call chat (default `false`). | | `enable_screenshare` | bool | Allow screen sharing (default `true`). | | `enable_knocking` | bool | Lobby with knock/admit for private rooms. | | `enable_prejoin_ui` | bool | Waiting room with device checks. | | `enable_dialin` / `enable_dialout` | bool | Allow PSTN dial-in / dial-out. | | `enable_transcription_storage` | bool | Save Daily transcriptions as WebVTT. | | `permissions` | object | Default permissions for non-owner participants. | | `recordings_bucket` | object | Custom S3 bucket for Daily cloud recordings. | This is the testing-relevant subset; any key from the [Daily room config reference](https://docs.daily.co/reference/rest-api/rooms/config) is accepted and passed through. > **Note** > > This JSON only applies in **"We create rooms"** mode. In **"You create rooms"** mode *you* create the room, so you set these properties yourself in your own `POST /rooms` call. --- ## Choosing a mode ### Do you want RubricHQ to hold your Daily API key? * **No** → use **You create rooms** (`client`). Implement `create-and-join-daily`. We never see your key. * **Yes** → use **We create rooms** (`rubric`). Implement `POST /api/session` to join the given room. --- ## Results When the call ends, the **transcript**, **audio recording** (speaker-separated when available), and **metrics** appear automatically on the run in RubricHQ — your bot runner doesn't need to report anything back. If a call can't proceed (missing/incorrect credentials, room creation failed, or the bot never joins) the run is marked **failed** with the reason rather than left hanging. > **Tip** > > A reference Pipecat bot runner that supports **both** modes only needs two endpoints: `POST /api/create-and-join-daily` (client mode) and `POST /api/session` (rubric mode). Everything else — recording, transcription, metrics — is handled by RubricHQ.