> ## Documentation Index > Fetch the complete documentation index at: https://docs.miraiminds.co/llms.txt > Use this file to discover all available pages before exploring further. # Rebuild insights > Counts the report again from scratch instead of serving the cached one. Call summaries and outcomes can arrive a few minutes after a call ends, so rebuild when the outcome numbers look behind. No body, no charge. ## OpenAPI ````yaml /api-reference/openapi.json post /v2/campaigns/{campaign_id}/insights openapi: 3.1.0 info: title: Mirai Voice API version: 2026-10-15.analysis-templates description: >- The v2 API for voice agents, calls, campaigns, phone numbers and speech. Every request carries `Authorization: Bearer sk_live_…`. Generated from the API's own contract and its Postman collection. servers: - url: https://sandbox.voice.miraiminds.co description: 'Sandbox: trial workspaces, before your company goes live' - url: https://prod.voice.miraiminds.co description: 'Production: workspaces that have gone live' security: - bearerAuth: [] tags: - name: Agents description: >- An agent is what a call runs: its prompt (or a node flow, see the Flows section), voice, language and limits. Write it once and dial it as often as you like; each call fills in its own `variables`. Every save creates a new revision. You can read old revisions, roll back to one, and publish a draft when it is ready. None of the requests here place a call or charge your wallet. - name: Calls description: >- Place a call, follow it while it runs, then read what happened: the transcript, the recording, the post-call analysis. `POST /v2/calls` answers before the phone rings, with an id. Everything after that is about that id. Live control and the live event stream work on browser calls (`channel: "web"`) and realtime sessions only; a phone call answers them with `400 unsupported_channel`. - name: Flows description: >- A node-based agent runs the call as a graph of steps. Each node has its own instructions, and the agent moves to the next node when a transition's condition is met, so a call with branches (wrong person, not now, reschedule) stays easy to follow and to change. The usual path: draft a graph from a brief or from recordings of your real calls, check it, test it with simulated calls, then save it on an agent. Drafting, transcribing and testing use AI models and charge your wallet; checking, saving and reading are free. Full guide: https://docs.miraiminds.co/v2/node-agents - name: Tools and secrets description: >- Connect your own APIs to an agent. A tool runs at one of three moments: * `pre_call`, before dialling: fetch context for the greeting, or skip the call. * `on_call`, when the agent decides to use it mid-conversation: look something up, book something. * `post_call`, after the call has settled: send the outcome to your CRM, schedule a call back. The order here is the order you'd use them in: see what's available, store your credential as a secret, add a tool, test it against your endpoint, then read each call's tool runs. Tools themselves cost nothing extra. Tool definitions use Mirai's own templates, like `{{ args.date }}` and `{{ secrets.crm_key }}`. A definition that doesn't validate comes back as a list, so you can fix everything at once: `{"error": "invalid_tools", "details": [{"path", "message"}]}`. Everything else uses the usual `{"error": {"code", "message"}}`. - name: Campaigns description: >- Call a whole list with one agent. Upload contacts, say which days and hours the campaign may ring, and start it. From then on it dials by itself: it paces itself, waits overnight, retries calls that didn't connect, skips numbers on your do-not-call list, and pauses itself when its budget or your wallet runs out. Campaign calls are ordinary calls. They show up in `GET /v2/calls`, send the same `call.*` webhooks and bill the same per-minute rate. In a sandbox workspace every campaign runs and bills at T5 (₹5 a minute), whatever tier you ask for. Money on a campaign is in **paise**: `"budget_paise": 50000` is ₹500. The requests run top to bottom: create saves `campaign_id`, and the rest use it. Starting a campaign rings every contact on it, so put numbers you're allowed to call in the bodies first. - name: Do-not-call list description: >- Numbers your campaigns will never dial. The list covers every campaign in the workspace, including ones that are already running: it's checked at the moment a contact is about to be called, so a number added mid-campaign is skipped from then on. A skipped contact stays in its campaign as `suppressed` and costs nothing. It doesn't apply to single calls placed with `POST /v2/calls`; check the list yourself before those if you need to. It's your own list, not the national DND register, and adding a number here doesn't meet your DND obligations. - name: Phone numbers description: >- The numbers your agents answer. Each one comes from the **Telephony** section: * **Rented from Mirai.** Once the rental is active, the number shows up here by itself (`ownership: managed`). * **From your own Plivo account.** Connect the account in Telephony, list its numbers, then bring one here with [Import a Plivo number](/api-reference/phone-numbers/import-a-plivo-number) (`ownership: customer`). Plivo keeps billing you for it. After that it's two steps, in this order: [Assign an agent](/api-reference/phone-numbers/assign-an-agent) (who answers), then [Turn on incoming calls](/api-reference/phone-numbers/turn-on-incoming-calls). `state` is `imported` until calls are on and `ready` after; `error` means the last attempt to turn calls on failed, and `setup_error` says why. Every change sends the number's current `version`, and each change raises it by one. If you're not sure what it is, read the number first; a stale version is a 409 `conflict` and changes nothing. To call out from one of your numbers, place a call with `phone_number_id` set to its id once it is `ready` (Indian destinations only). Calls on your numbers are billed like any other call. Every number also says how it is doing in `health`: `state` is `active`, `warming` (its first week, at half its pool's pace), `resting`, `cooling` (rested three times in a day; waits for you) or `retired`, with this hour's attempts and seven days of answers. You can rest, resume and retire your own numbers; a resting or retired number still answers calls to it. - name: Phone pools description: >- A pool is a group of your own phone numbers that a campaign, an agent or a single call can ring from. Each call takes the number best placed for it: a number a contact has already been rung from stays theirs on a retry, numbers in the contact's own circle come first, and the pool's pace (`max_per_hour`, per number) is held across every campaign and API call at once. A number whose answers drop well below its pool-mates' rests on its own for 45 minutes. Point a campaign at a pool with `pool_id` on [Create a campaign](/api-reference/campaigns/create-a-campaign), an agent with `calls_from: {"pool_id": …}`, or one call with `pool_id` on [Place a call](/api-reference/calls/place-a-call). `pool_id` and `phone_number_id` never go together. With nothing chosen, calls come from the agent's setting, then the pool marked `default_for_campaigns`, then the Mirai shared line. A call's `calls_from_source` is `pool` (with `pool_id`) when a pool picked its number. A single call on a pool whose numbers are all resting or at their pace this hour answers 409 `pool_busy` with `Retry-After`; one with no number that can call, 409 `pool_unavailable`. A campaign doesn't fail: it waits and carries on. `purpose` is what the calls are for: `outreach` (promotional), `reminders`, `support` or `other`. It sets the starting pace: 40 an hour for support, 60 otherwise. Pools are free; numbers are billed as numbers. - name: Telephony description: >- Getting a phone number for your agent. There are two ways, and a workspace can use both. **1. Rent a number from Mirai.** ₹500 a month, paid as ₹1,500 from your wallet every three months, renewing until you turn it off. Indian numbers need a business verification that Plivo approves once: read the requirements, submit your details and documents, then refresh until it's `accepted`. After that: search, quote, rent. The rented number appears in **Phone numbers** by itself. **2. Connect your own Plivo account.** Plivo keeps billing you directly. Connect it with your Auth ID and Auth Token, list the numbers it owns, and bring one over with [Import a Plivo number](/api-reference/phone-numbers/import-a-plivo-number). A Plivo main account can also rent new numbers through the same search → quote → rent requests, with its connection id as `account`. Either way you finish in **Phone numbers**: assign the agent that answers, then turn on incoming calls. The last two requests verify your own phone, so the workspace can ring it from Mirai's shared test number (test calls are placed from the Numbers page in the console). Indian (+91) numbers only for now. If phone numbers aren't available on the host you're calling, every request here answers 503 `telephony_unavailable`. - name: Transcriptions description: >- Turn a recorded call (or any recording) into a transcript with speakers and timestamps. Hindi, English, Gujarati and mixed speech are written the way they were spoken, never translated. ₹18 per hour of audio; failed and degraded jobs are free. - name: Speech to text description: >- Speech to text in ten languages, two ways: send one recording and get its text back in the same request ([Transcribe a recording](/api-reference/speech-to-text/transcribe-a-recording)), or stream live audio over one WebSocket per call and read partial transcripts while people speak, then one final transcript per utterance. Language codes: hi-IN, en-IN, gu-IN, mr-IN, pa-IN, bn-IN, ta-IN, te-IN, kn-IN or ml-IN. `wss://sandbox.voice.miraiminds.co/v1/audio/transcriptions/stream?language_code=hi-IN&encoding=mulaw&sample_rate=8000&endpointing=manual` (`wss://prod.voice.miraiminds.co` once your company has gone live), with the header `Authorization: Bearer sk_live_YOUR_API_KEY`. 8 or 16 kHz, 16-bit PCM, μ-law or A-law. A browser uses `?token=` from [Mint stream tokens](/api-reference/speech-to-text/mint-stream-tokens) instead, because it cannot set headers on a WebSocket. Send JSON text frames: `{"event": "speech_start"}`, then `{"event": "audio_input", "audio": ""}` as the audio arrives, then `{"event": "speech_end"}`; `{"event": "end"}` closes the session. You receive `session.begin` first, `transcript.partial` while an utterance is open, exactly one `transcript.final` per utterance, and `session.end` with `audio_seconds_billed` and `cost_paise`. Every event, both endpointing modes, limits and errors: https://docs.miraiminds.co/v2/stt-quickstart - name: Text to speech description: >- Turn text into speech in one request, and read back what each request cost. - name: Wallet description: >- Your prepaid balance and every line that moved it. Calls, text to speech, flow drafts, transcriptions and number rentals all debit the same wallet. - name: Reference description: The voice catalogue, and the API contract as a machine-readable document. paths: /v2/campaigns/{campaign_id}/insights: post: tags: - Campaigns summary: Rebuild insights description: >- Counts the report again from scratch instead of serving the cached one. Call summaries and outcomes can arrive a few minutes after a call ends, so rebuild when the outcome numbers look behind. No body, no charge. operationId: rebuild_insights parameters: - name: campaign_id in: path required: true description: The campaign's id (`cmp_…`). schema: type: string example: cmp_01K79Q4T6W8XZ2B5D7F9H3JKMN responses: '200': description: Freshly counted content: application/json: examples: Freshly counted: summary: 200 — freshly counted value: object: campaign_insights schema: insights.v1.6 campaign_id: cmp_01K79Q4T6W8XZ2B5D7F9H3JKMN funnel: tier: measured stage_order: - list - valid - deduped - dialable - attempted - reached_the_network - connected - conversation - classified stages: list: 3 valid: 3 deduped: 3 dialable: 3 attempted: 3 reached_the_network: 3 connected: 2 conversation: 2 classified: 2 rates: answer_rate_pct: 66.7 conversation_rate_pct: 100 classified_rate_pct: 100 failed_before_media: value: 0 tier: measured reasons: {} note: >- dials that never connected audio (a carrier or platform outage), neither an answer nor a rejection not_attempted: value: 0 tier: measured connected_without_speech: value: 0 tier: measured retry_effectiveness: value: 0 tier: measured contacts_retried: 1 answered_after_a_retry: 0 note: >- attempts is the contact's total; this is 'answered with more than one attempt recorded', not per-attempt history outcomes: tier: measured conversations: 2 counts: booked: 1 will_call_back: 1 percent_of_conversations: booked: 50 will_call_back: 50 warm: value: 2 tier: assumption_based assumptions_used: - C7 definition: - booked - callback_human - will_call_back percent_of_conversations: 100 unclassified: value: 0 tier: measured analysis_not_run: 0 analysis_returned_no_outcome: 0 connected_but_nobody_spoke: 0 never_reached: 1 bookings: value: - name: राहुल phone: '+919876543210' call_id: call_01K2M4RB8CDEFGHJKMNPQRST contact_id: lead-1041 summary: ग्राहक ने 18 अक्टूबर सुबह 10 बजे की सर्विस बुक की। when: 18 अक्टूबर, सुबह 10 बजे tier: measured callbacks: value: - name: अमित phone: '+919876501234' call_id: call_01K7D3G5J7M9P1R3T5V7X9Z1B4 contact_id: lead-1043 summary: >- ग्राहक अभी गाड़ी चला रहे थे, शाम को खुद कॉल करेंगे। when: '' tier: measured handoffs: value: [] tier: measured label_confidence: tier: assumption_based assumptions_used: - C6 value: null note: outcome labels are AI-classified (±5-10%) money: tier: measured source: wallet_ledger total_spend_inr: value: 15 tier: measured debit_inr: 15 credit_inr: 0 calls_charged: 2 calls_without_ledger_line: 1 ledger_truncated: false scope_note: costs counted are call charges only talk_minutes: value: 1.87 tier: measured talk_seconds: 112 billed_minutes: value: 3 tier: measured charged_calls: 2 calls_under_one_minute: 1 source: wallet_ledger from_statement: 2 from_rule: 0 rule: 'per call: ceil(duration / 60), minimum 1' expected_by_rule: 3 matches_rule: true billed_vs_talk_note: >- 3 minutes were billed against 1.87 minutes of talk time because billing is per call, rounded up, with a one-minute minimum — 1 of the 2 charged calls lasted under a minute. cost_per_conversation_inr: value: 7.5 tier: measured conversations: 2 cost_per_booking_inr: value: 15 tier: measured bookings: 1 cost_per_warm_inr: value: 7.5 tier: assumption_based assumptions_used: - C7 warm: 2 cost_per_talk_minute_inr: value: 8.02 tier: measured vs_human: value: -0.04 tier: assumption_based assumptions_used: - C4 human_cost_inr: 14.96 human_rate_inr_per_min: 8 machine_cost_inr: 15 expected_pipeline_inr: value: 1950 tier: assumption_based assumptions_used: - C1 - C2 - C3 - C7 bookings: 1 warm: 2 roi_statement: value: ₹15.0 spent → ₹1950.0 expected pipeline tier: assumption_based assumptions_used: - C1 - C2 - C3 - C7 ops: tier: measured calls_without_timestamps: value: 1 tier: measured dialled: 3 note: >- a call record whose start stamp is missing or is a zero value; excluded from the wall clock, the concurrency sweep and the hour histogram talk_total_secs: value: 112 tier: measured talk_avg_secs: value: 56 tier: measured calls: 2 talk_p50_secs: value: 44 tier: measured talk_max_secs: value: 68 tier: measured answer_rate_by_hour: value: '10': attempted: 2 connected: 2 conversations: 2 answer_rate_pct: 100 '11': attempted: 1 connected: 0 conversations: 0 answer_rate_pct: 0 tier: measured timezone: Asia/Kolkata timezone_source: zoneinfo basis: started_at, else created_at (the dial moment) bucketed_by_created_at: 1 attempts_without_a_timestamp: 0 peak_concurrency_upper_bound: value: 1 tier: measured method: >- sweep over started_at + duration_secs, whole-second stamps calls_with_a_full_window: 2 calls_missing_a_window: 1 configured_max_concurrent: 3 exceeds_configured: false wall_clock_secs: value: 3664 tier: measured first_call_at: '2026-10-12T04:30:48+00:00' last_call_ended_at: '2026-10-12T05:31:52+00:00' quality: tier: measured voice_to_voice_p50_ms: value: 790 tier: measured calls_measured: 2 calls_unmeasured: 1 sources: telemetry_v2v: 2 calls_discarded_implausible: 0 floor_ms: 200 voice_to_voice_p90_ms: value: 820 tier: measured calls_measured: 2 turn_end_to_end_p50_ms: value: null tier: measured calls_measured: 0 definition: user stopped speaking -> bot stopped speaking turns_per_conversation_avg: value: 6.5 tier: measured p50: 5 conversations_counted: 2 barge_ins_total: value: 0 tier: measured calls_with_turn_timing: 2 calls_without_turn_timing: 1 method: transcript_overlap is_lower_bound: true definition: a user turn that began before the bot's turn ended note: >- a lower bound: an interruption that produced no transcribed user turn is not counted short_call_rate_pct: value: 0 tier: measured threshold_secs: 15 calls: 0 of: conversations engaged_rate_pct: value: 50 tier: measured threshold_secs: 60 calls: 1 of: conversations hygiene: tier: measured invalid_numbers: value: 0 tier: measured reasons: {} rows: [] duplicate_phones: value: 0 tier: measured extra_rows: 0 rows: [] wrong_numbers: value: 0 tier: measured rows: [] recently_serviced_contradictions: value: 0 tier: measured rows: [] unreachable: value: 1 tier: measured rows: - phone: '+919812345678' name: प्रिया attempts: 2 status: exhausted last_status: no_answer note: busy / no-answer is not a rejection cleanup_value_inr: value: 0 tier: assumption_based assumptions_used: - C5 corrected_records: 0 deliverables: tier: measured csv_url: >- /v2/campaigns/cmp_01K79Q4T6W8XZ2B5D7F9H3JKMN/report?format=csv csv_columns: - id - phone - name - due_date - vehicle - status - attempts - last_call_id - started_at - duration_secs - ended_reason - cost_inr - outcome - success - summary - transcript - recording_url csv_variable_columns: - due_date - vehicle recordings: value: 2 tier: measured expected: 2 missing: 0 link_expiry_days: 7 basis: call records that name a recording object transcripts: value: 2 tier: measured expected: 2 missing: 0 call_records: value: 3 tier: measured expected: 3 contacts_never_dialled: 0 cited_calls: call_01K2M4RB8CDEFGHJKMNPQRST: name: राहुल phone_masked: •••••••••3210 outcome: booked duration_secs: 68 turns: - role: assistant text: >- नमस्ते, मैं आशु बोल रहा हूं मिराई मोटर्स से. एक मिनट है आपके पास? - role: user text: हाँ बोलिए - role: assistant text: >- आपकी स्विफ्ट की सर्विस 18 अक्टूबर को ड्यू है. स्लॉट बुक कर दूं? - role: user text: हाँ, सुबह 10 बजे कर दीजिए recording: true call_01K7D3G5J7M9P1R3T5V7X9Z1B4: name: अमित phone_masked: •••••••••1234 outcome: will_call_back duration_secs: 44 turns: - role: assistant text: >- नमस्ते, मैं आशु बोल रहा हूं मिराई मोटर्स से. एक मिनट है आपके पास? - role: user text: अभी ड्राइव कर रहा हूं, शाम को कॉल करता हूं recording: true assumptions: C1: label: average service ticket value: 1500 unit: inr source: default C2: label: warm-lead close rate value: 0.3 unit: rate source: default C3: label: booking show-up rate value: 0.7 unit: rate source: default C4: label: human telecaller cost value: 8 unit: inr_per_min source: default C5: label: value of one corrected CRM record value: 10 unit: inr source: default C6: label: outcome labels are AI-classified (±5-10%) value: null unit: note source: default C7: label: warm = booked + will_call_back + callback_human value: - booked - will_call_back - callback_human unit: outcome_set source: default C8: label: costs counted are call charges only value: null unit: note source: default C9: label: recording links expire value: 7 unit: days source: default C10: label: busy / no-answer is not a rejection value: null unit: note source: default meta: workspace_id: ws_3f9a1c27d8e4b610 generated_at: '2026-10-12T06:02:11Z' data_version: insights.v1.6|2026-10-12T05:41:09Z|completed|1500 campaign: name: सर्विस रिमाइंडर — अक्टूबर status: completed tier: t5 agent_id: agt_01K2M4P7QRSTVWXYZ0A1B2C3 timezone: Asia/Kolkata created_at: '2026-10-09T06:12:40Z' updated_at: '2026-10-12T05:41:09Z' contacts_read: 3 calls_named: 3 call_records_found: 3 call_records_missing: 0 calls_without_timestamps: 1 calls_failed_before_media: 0 contacts_with_multiple_attempts: 0 representative_overrides: 0 attempts_recovered: 0 group: null cited_calls_carried: 2 cited_calls_truncated: false cited_calls_max: 80 cited_transcript_chars: 269 ledger_transactions_scanned: 2 ledger_truncated: false tiers_present: - measured - assumption_based contacts_truncated: false served_from_cache: false '404': description: Not in this workspace content: application/json: examples: Not in this workspace: summary: 404 — not in this workspace value: error: code: not_found message: no campaign cmp_01K79Q4T6W8XZ2B5D7F9H3JKMN components: securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your workspace secret key, `sk_live_` followed by 32 hex characters. Create one in the console under **Developers**. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.