> ## 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. # Create a transcription > Upload a recording (up to 45 MB, up to two hours, any common audio format) and get a job back straight away with `202`. Then read it with [Get a transcription](/api-reference/transcriptions/get-a-transcription) until `status` is `completed` or `failed`. Pick the file in the `file` field before you send. `context` and `vocabulary` are optional but help a lot with names and brand terms. Prefer to send a link? Switch the body to raw JSON with an `https` `url` (up to 200 MB) instead of `file`; every other field is the same. The `Idempotency-Key` makes a retry safe: the same key returns the job it already created, with no second charge. ## OpenAPI ````yaml /api-reference/openapi.json post /v2/transcriptions 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/transcriptions: post: tags: - Transcriptions summary: Create a transcription description: >- Upload a recording (up to 45 MB, up to two hours, any common audio format) and get a job back straight away with `202`. Then read it with [Get a transcription](/api-reference/transcriptions/get-a-transcription) until `status` is `completed` or `failed`. Pick the file in the `file` field before you send. `context` and `vocabulary` are optional but help a lot with names and brand terms. Prefer to send a link? Switch the body to raw JSON with an `https` `url` (up to 200 MB) instead of `file`; every other field is the same. The `Idempotency-Key` makes a retry safe: the same key returns the job it already created, with no second charge. operationId: create_transcription parameters: - name: Idempotency-Key in: header required: false description: >- Up to 255 characters. The same key within 24 hours replays the first answer and creates nothing new. Build it from your own record, such as `order-8842-reminder-1`. schema: maxLength: 255 type: string example: order-8842-reminder-1 requestBody: required: true content: multipart/form-data: schema: type: object properties: file: type: string format: binary description: The recording. One file per request. context: type: string example: >- A call to a university admissions desk about a course and its fees description: Who is calling whom and why. Up to 2,000 characters. vocabulary: type: string example: Mira University, BBA, Aadhaar description: Names and terms to spell right, comma or newline separated. language: type: string description: auto (default), hi, gu, en, mr, pa, bn or ur. diarize: type: string description: Speaker separation. Default true. words: type: string description: Word timings on each segment. Default false. required: - file responses: '202': description: Accepted content: application/json: schema: $ref: '#/components/schemas/Transcription' examples: Accepted: summary: 202 — accepted value: id: trn_01M3XRSFXW77RHEQ85979AJXAF object: transcription status: queued created_at: '2026-10-02T07:38:20Z' finished_at: null duration_s: null degraded: null model: null source: upload file_name: call.wav bytes: 370308 language: null diarize: true words: false error: null cost: status: pending amount_inr: null rate_inr_per_hour: 18 '402': description: The wallet is empty content: application/json: examples: The wallet is empty: summary: 402 — the wallet is empty value: error: code: insufficient_balance message: >- wallet balance 0.00 INR is empty; transcribing a recording needs a positive balance '429': description: 20 jobs already running content: application/json: examples: 20 jobs already running: summary: 429 — 20 jobs already running value: error: code: at_capacity message: >- this workspace already has 20 transcriptions in progress (the limit is 20); retry when one finishes components: schemas: Transcription: description: >- An offline transcription job. Lists carry the job without text, segments, draft or diarization; GET /v2/transcriptions/{id} adds them. properties: bytes: minimum: 0 type: integer cost: description: >- Billing: pending until the job finishes; then charged once (₹18 per hour of audio, rounded up to a paisa) or free (degraded or failed). amount_inr is the job's charge at the rate frozen when it was accepted; the wallet transaction (kind transcription, reference = the job id) records what the balance moved. properties: amount_inr: minimum: 0 type: - number - 'null' rate_inr_per_hour: type: number status: enum: - pending - charged - free type: string required: - status - amount_inr - rate_inr_per_hour type: object created_at: format: date-time type: string degraded: description: >- Once completed: true when the merge step was unavailable, so text is a single decoding pass without speaker roles; a degraded job is free. null until completed. type: - boolean - 'null' diarization: description: Completed jobs, GET by id only. properties: applied: type: boolean enabled: type: boolean non_speech: description: >- Parts of the recording that were not speech, such as ringing or a caller tune, and were left out of the transcript. Absent when nothing was left out. items: properties: end: minimum: 0 type: number start: description: Seconds from the start of the recording. minimum: 0 type: number required: - start - end type: object type: array speakers: description: >- One entry per voice, in speaker_id order (spk0 first): the agent is spk0 and the customer spk1 on a call between them. items: properties: id: description: The speaker_id its segments carry. type: string role: description: Agent, Customer or Other. type: string talk_s: description: Seconds this voice talked. type: number type: object type: array words: properties: applied: type: boolean type: object type: object diarize: type: boolean draft: description: >- While merging, GET by id only: the strongest single decoding pass, readable seconds after decoding and before the merge finishes. Speaker is empty. Replaced by segments once completed. items: $ref: '#/components/schemas/TranscriptionSegment' type: array duration_s: description: The recording's length in seconds, known once decoding has started. minimum: 0 type: - number - 'null' error: description: >- Why a failed job failed. transcription_failed and audio_too_long are the recording's fault (not audio, damaged, empty, or too long); every other code is a fault on our side, and the same recording can be submitted again. A failed job is free. properties: code: enum: - transcription_failed - audio_too_long - upstream_unavailable - engine_restarted - job_lost - timed_out - submit_interrupted type: string message: type: string type: - object - 'null' file_name: type: string finished_at: format: date-time type: - string - 'null' id: description: >- The job id; also the reference of its wallet transaction (kind transcription). pattern: ^trn_[0-9A-Z]{26}$ type: string language: description: The language you forced, or null for automatic detection. type: - string - 'null' model: description: >- The model that produced the transcript, once completed (mira-transcribe-offline-1). type: - string - 'null' object: const: transcription segments: description: Completed jobs, GET by id only. items: $ref: '#/components/schemas/TranscriptionSegment' type: array source: enum: - upload - url type: string status: description: >- queued → decoding → merging → completed | failed; there is no progress figure. A job typically completes in about 10 seconds plus 15% of the recording's length; diarization adds about a second. enum: - queued - decoding - merging - completed - failed type: string text: description: The whole transcript; completed jobs, GET by id only. type: string words: type: boolean required: - id - object - status - created_at - finished_at - duration_s - degraded - model - source - file_name - bytes - language - diarize - words - error - cost type: object TranscriptionSegment: properties: end: minimum: 0 type: number speaker: description: >- The party: Agent, Customer or Other; empty when it could not be told (a degraded job, or the draft). type: string speaker_id: description: >- The voice, per recording (spk0, spk1, …). Agent voices are numbered first, then Customer voices, then any others, each in order of first appearance, so on a call between an agent and a customer the agent is spk0 and the customer spk1. Present when diarization was applied. type: string start: description: Seconds from the start of the recording. minimum: 0 type: number text: type: string words: description: Present when words was requested and the call aligned. items: properties: end: type: number start: type: number w: type: string required: - w - start - end type: object type: array required: - speaker - start - end - text type: object 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.