Speko

List the STT/LLM/TTS/S2S provider and model catalog. Each entry's `id` ('vendor' or 'vendor:model') is the literal string accepted by `allowedProviders` pins in agent and session configs; `benchmarked` marks entries with live Speko benchmark scores. STT and TTS entries carry `priced`: on audio.synthesize and audio.transcribe, a `priced: false` model is skipped on Speko-managed keys (the request fails if no priced model is left) and works only with the caller's own provider key, so pin a `priced: true` model for managed usage.

models.list

List sessions for the authenticated organization.

sessions.list

List the Speko TTS voice catalog: voices (vendor, id, name) plus TTS providers with their models. Use a returned voice id as the `voice` field on agents.create or POST /v1/sessions bodies.

voices.list

Read this workspace's phone compliance status. OAuth connector workspaces submit automatically from the phone authorization accepted during sign-in; do not collect or submit declaration fields in chat. `submissionMode` identifies automatic OAuth, manual dashboard/API, or grandfathered migration handling.

phone_numbers.kyb.get

List phone and SIP numbers owned by the current workspace. For OAuth connectors, the first outbound call automatically provisions a dedicated number from workspace credits when none exists. Manual dashboard/API users keep the explicit declaration and purchase flow.

phone_numbers.list

Preview the THREE voice-stack options before creating an agent — so the user picks. Returns the same recommendation the dashboard's agent-create shows, as three tiers. Present them to the user with these labels and each tier's STT / LLM / TTS: premium -> "Quality" balanced -> "Fastest" cost_optimized -> "Cheapest" Ask which one they want (and confirm the region — default USA). Then call create_agent with the chosen objective mapped to intent.optimizeFor: Quality -> 'quality', Fastest -> 'latency', Cheapest -> 'cost' plus intent.region. The server then pins that tier's failover stack automatically, so the created agent matches exactly what you previewed.

agents.preview_stacks

Search bundled Speko docs. Returns slug, title, score, snippet. Use this to look up SDK usage, API request/body shapes, and migration steps without leaving the MCP session. For example, after a Speko API validation error, search the failing field name to find the correct shape. Each hit's `slug` can be opened as the `spekoai://docs/{slug}` resource; `spekoai://docs/index` lists every bundled doc.

docs.search

Get the ordered transcript and per-turn latency for a workspace session, including any tool calls made mid-call (toolCalls, by name and args) and a latencyStatus per turn ("partial"|"complete"|"interrupted"|"error"). Use this to confirm whether a keypad press (send_dtmf) was invoked, or whether a turn with no agent text and an "error" latency status points to a synthesis failure rather than the callee hanging up.

sessions.transcript.get

Open a support ticket with the Speko team on behalf of the signed-in user. summary is one line (3-200 characters); details is the full description (up to 4,000 characters). category is billing, calls, setup or other (default other). related optionally carries ids the team should look at: sessionId, callId, agentId, phoneNumber. Ids only: recordings and transcripts are never attached. Returns ticketId and expectedResponse; the user also receives a confirmation email and the team replies to that email address. Returns 429 SUPPORT_TICKET_RATE_LIMITED after too many tickets in a short time; the error says when to retry. A ticket is stored even when the team notification is delayed, so a success never needs a resend.

support.ticket.create

Synthesize speech from text, returning base64 audio. Routed across TTS providers by the intent. The audio is returned as base64 with its content type and sample rate so a client can save or play it. Served by the Speko Router when the request is one the Router's speech body can express, and by the Platform endpoint otherwise — a request naming `speed`, `instructions`, `spokenForm`, a bare `model` or more than one allowed provider keeps the knob it asked for rather than losing it.

audio.synthesize

Start an agent-to-agent test call. Dispatches the agent under test plus a caller (a persona synthesized from `objective`, or another agent via `caller_agent_id`) into ONE LiveKit room with NO phone/SIP leg — so it CANNOT hairpin the way dialing the agent's own number does. Returns immediately with a RUN id and status 'queued' - NOT a session id. Review it in THREE separately bounded phases, polling about every 5 seconds. (1) Get the session id: poll agents.test_call.get(agent_id, runId) until `run.result.testCall.agentSessionId` appears - the worker publishes it once the call actually starts. RECORD that id the first time you see it and keep using it: the worker REPLACES `run.result` on timeout, retry and abort, so a later read can lose the id while the session itself lives on. If `run.status` reaches passed, failed or incomplete and you never saw an id, the call never started - report what `run.result` says. If it reaches aborted, the run hit its deadline or ran out of retries and its result was overwritten: a session may well exist, so recover it before reporting nothing. List candidates with agents.calls.list(agent_id, since=<dispatch time>), then IDENTIFY the right one by reading calls.get on each until `metadata.evalRunId` equals this runId and `metadata.runKind` is 'test_call'. Never just take the newest - another call on the same agent can start after your dispatch, and reviewing it would report the wrong transcript and recording as this test call's. Otherwise give up after ~24 checks. Never pass the run id to a call or session tool. (2) Wait for the call: poll calls.get(agentSessionId) until it reports the call ended, then read sessions.transcript.get(agentSessionId). Bound THIS phase by ttl_seconds PLUS ~60s of worker startup headroom - that sum is the run's own deadline - never by a check count. (3) Get the recording: it finalizes AFTER the call ends, so KEEP polling calls.get for a FURTHER ~24 checks, until `recording_status` reads 'ready', and only then call calls.recording.get(agentSessionId) - calling it earlier returns 404 by design. Stop at once if `recording_status` is failed, suppressed or discarded: that recording will never exist. Provide exactly one of objective / caller_agent_id / caller_system_prompt.

agents.test_call

Transcribe audio to text. Speech to text only: no audio is generated and none is returned. Google Drive's "can't scan for viruses" confirmation pages are refused as web pages; use a link that downloads the audio without a confirmation form.

audio.transcribe