aid: elsa
url: https://raw.githubusercontent.com/api-evangelist/elsa/refs/heads/main/apis.yml
name: ELSA
kind: company
description: ELSA (English Language Speech Assistant) builds AI speech-recognition and
  pronunciation-assessment technology for non-native English speakers, powering the ELSA
  Speak consumer app. The ELSA API is a partner/B2B speech-assessment service that scores
  recorded or streamed English audio across pronunciation, fluency, intonation, grammar,
  and vocabulary, returning sentence, word, and phoneme-level feedback.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- Speech Assessment
- Pronunciation
- Speech Recognition
- Language Learning
- AI
created: '2026-06-21'
modified: '2026-06-21'
specificationVersion: '0.19'
apis:
- aid: elsa:elsa-pronunciation-assessment-api
  name: ELSA Pronunciation Assessment API (Scripted)
  tags:
  - Pronunciation
  - Speech Assessment
  - Scripted
  - Phoneme Scoring
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://api-external-doc.elsanow.co/
  baseURL: https://api.elsanow.io/api/v2
  properties:
  - url: https://api-external-doc.elsanow.co/
    type: Documentation
  - url: https://api-external-doc.elsanow.co/category/api
    type: APIReference
  - url: openapi/elsa-openapi.yml
    type: OpenAPI
  description: Scripted speech scoring. The caller submits an audio recording together
    with the expected script/sentence and receives sentence, word, and phoneme-level
    pronunciation scores, mispronunciation hints, word stress, reading speed, pausing,
    fluency, and intonation. Batch scoring is a POST to /score_audio; a realtime variant
    streams audio over a WebSocket to /ws/score_audio.
- aid: elsa:elsa-realtime-streaming-speech-api
  name: ELSA Realtime Streaming Speech API
  tags:
  - Realtime
  - Streaming
  - WebSocket
  - Unscripted
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://api-external-doc.elsanow.co/websocket-scripted
  baseURL: wss://api.elsanow.io
  properties:
  - url: https://api-external-doc.elsanow.co/websocket-scripted
    type: Documentation
  - url: https://api-external-doc.elsanow.co/websocket-unscripted
    type: Documentation
  - url: openapi/elsa-openapi.yml
    type: OpenAPI
  description: Realtime, packet-by-packet audio scoring over WebSocket. Scripted streaming
    connects to wss://api.elsanow.io/api/v2/ws/score_audio and unscripted (open-ended)
    streaming connects to wss://api.elsanow.io/api/v1/ws/score_audio_plus, delivering
    incremental pronunciation, fluency, intonation, grammar, and vocabulary feedback.
- aid: elsa:elsa-unscripted-speech-assessment-api
  name: ELSA Unscripted Speech Assessment API
  tags:
  - Unscripted
  - Fluency
  - Grammar
  - Vocabulary
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://api-external-doc.elsanow.co/elsa/unscripted
  baseURL: https://api.elsanow.io/api/v1
  properties:
  - url: https://api-external-doc.elsanow.co/elsa/unscripted
    type: Documentation
  - url: https://api-external-doc.elsanow.co/category/api
    type: APIReference
  - url: openapi/elsa-openapi.yml
    type: OpenAPI
  description: Open-ended (unscripted) speech assessment. The caller submits spontaneous
    English audio with no reference script and receives a spoken transcript plus pronunciation,
    prosody/intonation, fluency, grammar, and vocabulary analysis with improvement
    suggestions. Batch scoring is a POST to /score_audio_plus.
common:
- type: GitHubOrganization
  url: https://github.com/elsa
- type: LinkedIn
  url: https://www.linkedin.com/company/elsacorp
- type: Website
  url: https://www.elsaspeak.com
- type: Documentation
  url: https://api-external-doc.elsanow.co/
- type: Plans
  url: plans/elsa-plans-pricing.yml
- type: RateLimits
  url: rate-limits/elsa-rate-limits.yml
- type: FinOps
  url: finops/elsa-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com