2s

2s Transcribe API

The transcribe API from 2s — 1 operation(s) for transcribe.

Operations 1

POST /api/transcribe/audio Transcribe an audio file to text #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/2s-io:2s-io-transcribe-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

2s-io-transcribe-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: 2s — the (most) everything Transcribe API
  version: '1'
  summary: The (most) everything API.
  description: 'The (most) everything API for AI agents: 575+ pay-per-call endpoints on one origin.'
  contact:
    name: 2s
    url: https://2s.io
    email: alley@2s.io
  x-logo:
    url: https://2s.io/icon-512.png
    altText: 2s
  x-guidance: 'Pay-per-call REST API for AI agents — hundreds of endpoints returning ground-truth data (US public records, company & legal identifiers, finance/SEC, crypto/web3, security & CVEs, medical codes, weather & geocoding, agriculture, energy, maritime, music, and more). Every endpoint is paid per call in USDC via x402 (Base or Solana) — no API key, no signup. Call any endpoint with no auth to get a 402 PaymentRequirements envelope, sign it (EIP-3009 on Base, partial SPL transfer on Solana), and retry with the PAYMENT-SIGNATURE header. Add ?trial=1 for one free real call per endpoint per hour to test before paying. To discover the right endpoint: GET https://2s.io/api/directory for the full catalog, or GET https://2s.io/api/search/endpoints?q=<natural-language task> for a ranked match. Per-call price is on each operation as x-payment-info (from $0.001). Batch up to 50 calls behind one payment via POST https://2s.io/api/batch/run.'
servers:
- url: https://2s.io
tags:
- name: transcribe
paths:
  /api/transcribe/audio:
    post:
      tags:
      - transcribe
      summary: Transcribe an audio file to text
      description: Transcribe an audio file to text. POST { url, language?, diarize? } — the audio is fetched from your URL (wav, mp3, m4a/aac, ogg/opus, flac, webm; up to 15 MB and 15 minutes per call — split longer recordings and call once per segment). Returns the full punctuated transcript, overall confidence, audio duration, detected or specified language (BCP-47, e.g. "en", "es"), word-level timestamps with confidences, and — with diarize=true — speaker-segmented utterances (who said what, when). High-accuracy speech recognition for meeting notes, podcast processing, voicemail handling, and media monitoring.
      operationId: transcribe_audio
      deprecated: false
      security:
      - x402Payment: []
      responses:
        '200':
          description: 'Normalized envelope: items = [one transcript] (full punctuated text, confidence, duration, language, word timestamps, optional speaker diarization); total = 1; meta.wordCount = word count.'
          content:
            application/json:
              schema:
                type: object
                required:
                - data
                - meta
                properties:
                  data:
                    type: object
                    properties:
                      ok:
                        type: boolean
                        enum:
                        - true
                      items:
                        type: array
                        items:
                          type: object
                          properties:
                            transcript:
                              type: string
                              description: Full punctuated transcript.
                            confidence:
                              type: number
                            durationSeconds:
                              type: number
                            language:
                              type: string
                              nullable: true
                            words:
                              type: array
                              items:
                                type: object
                                properties:
                                  word:
                                    type: string
                                  start:
                                    type: number
                                  end:
                                    type: number
                                  confidence:
                                    type: number
                                  speaker:
                                    type: number
                                    nullable: true
                                required:
                                - word
                                - start
                                - end
                                - confidence
                                - speaker
                                additionalProperties: false
                              description: Word-level timestamps (seconds).
                            utterances:
                              type: array
                              items:
                                type: object
                                properties:
                                  speaker:
                                    type: number
                                    nullable: true
                                  start:
                                    type: number
                                  end:
                                    type: number
                                  text:
                                    type: string
                                required:
                                - speaker
                                - start
                                - end
                                - text
                                additionalProperties: false
                              description: Speaker turns; populated when diarize=true.
                          required:
                          - transcript
                          - confidence
                          - durationSeconds
                          - language
                          - words
                          - utterances
                          additionalProperties: false
                      total:
                        type: integer
                        nullable: true
                        description: Total matching rows upstream; null when unknown.
                      source:
                        $ref: '#/components/schemas/Source'
                      meta:
                        type: object
                        properties:
                          wordCount:
                            type: integer
                            description: Number of words in the transcript.
                        required:
                        - wordCount
                        additionalProperties: false
                    required:
                    - ok
                    - items
                    - total
                    - source
                    additionalProperties: false
                  meta:
                    $ref: '#/components/schemas/CallMeta'
        '400':
          $ref: '#/components/responses/BadRequest'
        '402':
          $ref: '#/components/responses/PaymentRequired'
        '405':
          $ref: '#/components/responses/MethodNotAllowed'
        '500':
          $ref: '#/components/responses/ServerError'
        '502':
          $ref: '#/components/responses/UpstreamError'
      x-2s-id: transcribe.audio
      x-2s-version: null
      x-2s-price:
        usd: 0.32625
      x-2s-accepts:
      - x402
      x-2s-response-shape: normalized
      x-payment-info:
        price:
          mode: fixed
          currency: USD
          amount: '0.326250'
        protocols:
        - x402: {}
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                url:
                  type: string
                  format: uri
                  maxLength: 2048
                  description: 'Public audio URL. Caps: 15 MB, 15 minutes.'
                language:
                  type: string
                  pattern: ^[a-z]{2,3}(-[A-Za-z0-9]{2,8})?$
                  description: Two-letter ISO language code.
                diarize:
                  type: boolean
                  default: false
                  description: Diarize.
              required:
              - url
              additionalProperties: false
      parameters:
      - $ref: '#/components/parameters/TrialMode'
components:
  schemas:
    Source:
      type: object
      description: 'Provenance of the data: upstream provider, source URL, and license.'
      properties:
        provider:
          type: string
          description: Upstream data provider.
        url:
          type: string
          description: Source URL or documentation link.
        license:
          type: string
          description: License / usage terms for the data.
    CallMeta:
      type: object
      description: Per-call meta envelope — endpoint id, cost, caller kind, settlement details.
    X402PaymentRequiredV2:
      type: object
      description: x402 v2 PaymentRequired envelope. Pick any entry from accepts[], sign for that rail, retry with the PAYMENT-SIGNATURE header.
      required:
      - x402Version
      - accepts
      properties:
        x402Version:
          type: integer
          const: 2
        error:
          type: string
          description: Human-readable reason payment is required.
        resource:
          type: string
          description: The resource URL being purchased.
        accepts:
          type: array
          description: Payment requirement options, one per supported network (Base USDC, Solana USDC).
          items:
            type: object
            required:
            - scheme
            - network
            - amount
            - asset
            - payTo
            - maxTimeoutSeconds
            properties:
              scheme:
                type: string
                enum:
                - exact
              network:
                type: string
                description: CAIP-2 network id, e.g. "eip155:8453" (Base) or "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp".
              amount:
                type: string
                description: Price in atomic asset units (USDC has 6 decimals).
              asset:
                type: string
                description: Asset contract address / mint.
              payTo:
                type: string
                description: Treasury address to pay.
              maxTimeoutSeconds:
                type: integer
              extra:
                type: object
                description: 'Rail-specific extras (EVM: EIP-712 domain name/version; Solana: feePayer).'
                additionalProperties: true
        extensions:
          type: object
          description: Optional discovery metadata (e.g. bazaar input/output schemas).
          additionalProperties: true
  responses:
    PaymentRequired:
      description: Payment required. Body contains the x402 PaymentRequirements envelope with a multi-network accepts array; the per-call price is in accepts[].amount (and on the operation as x-2s-price). Sign for whichever rail you hold USDC on (EIP-3009 for Base, partial SPL transfer for Solana) and retry with the PAYMENT-SIGNATURE header (X-PAYMENT also accepted for v1 clients).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/X402PaymentRequiredV2'
    UpstreamError:
      description: Upstream provider error.
    MethodNotAllowed:
      description: Method not allowed — see `Allow` header for the supported method.
    ServerError:
      description: Internal server error.
    BadRequest:
      description: Bad request — invalid parameters.
  parameters:
    TrialMode:
      name: trial
      in: query
      required: false
      description: 'Try before you buy. Set to 1 for one free real call per endpoint per hour — no wallet or payment needed — to verify the endpoint before paying. Equivalent to sending the "X-2s-Trial: 1" request header. Works on every endpoint.'
      schema:
        type: integer
        enum:
        - 1
  securitySchemes:
    x402Payment:
      type: apiKey
      in: header
      name: PAYMENT-SIGNATURE
      description: 'x402 protocol v2: base64-encoded PaymentPayload. Call any paid endpoint without auth to receive a 402 with a multi-network PaymentRequirements envelope. Sign for either rail: EIP-3009 transferWithAuthorization (Base USDC) OR a partial SPL token transfer (Solana USDC). Retry with PAYMENT-SIGNATURE header. X-PAYMENT is also accepted for v1 buyer clients. See https://x402.org.'