aid: wellsaid
url: https://raw.githubusercontent.com/api-evangelist/wellsaid/refs/heads/main/apis.yml
name: WellSaid Labs
kind: company
description: WellSaid Labs is an AI text-to-speech voice platform. Its REST API renders
  natural-sounding speech from text using studio-quality voice avatars, supporting
  synchronous clip creation, low-latency audio streaming, and word-level timing with
  subtitles, authenticated with an X-Api-Key header.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- Text to Speech
- Voice
- Audio
- TTS
created: '2026-06-21'
modified: '2026-06-21'
specificationVersion: '0.19'
apis:
- aid: wellsaid:wellsaid-text-to-speech-api
  name: WellSaid Text-to-Speech API
  tags:
  - Text to Speech
  - Audio
  - Clips
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.wellsaidlabs.com/reference/getting-started-with-your-api
  baseURL: https://api.wellsaidlabs.com/v1
  properties:
  - url: https://docs.wellsaidlabs.com/reference/getting-started-with-your-api
    type: Documentation
  - url: https://docs.wellsaidlabs.com/reference
    type: APIReference
  - url: openapi/wellsaid-openapi.yml
    type: OpenAPI
  - url: collections/wellsaid.postman_collection.json
    type: PostmanCollection
  - url: collections/wellsaid.opencollection.json
    type: OpenCollection
  description: Render text to speech using studio-quality voice avatars. Create clips
    asynchronously (POST /tts/clips), list and retrieve rendered clips, and combine
    multiple clips into a single file with custom pauses.
- aid: wellsaid:wellsaid-streaming-tts-api
  name: WellSaid Streaming TTS API
  tags:
  - Streaming
  - Text to Speech
  - Audio
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.wellsaidlabs.com/reference/ttsstream
  baseURL: https://api.wellsaidlabs.com/v1
  properties:
  - url: https://docs.wellsaidlabs.com/reference/ttsstream
    type: Documentation
  - url: https://docs.wellsaidlabs.com/reference
    type: APIReference
  - url: openapi/wellsaid-openapi.yml
    type: OpenAPI
  - url: collections/wellsaid.postman_collection.json
    type: PostmanCollection
  - url: collections/wellsaid.opencollection.json
    type: OpenCollection
  description: Low-latency streaming text-to-speech (POST /tts/stream) that returns
    an audio/mpeg (MP3) stream as the render is produced, plus word-timing renders
    (POST /tts/word-timing) returning audio with JSON/SRT/VTT subtitle timing.
- aid: wellsaid:wellsaid-voices-speakers-api
  name: WellSaid Voices and Speakers API
  tags:
  - Voices
  - Speakers
  - Avatars
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.wellsaidlabs.com/reference/available-voice-avatars
  baseURL: https://api.wellsaidlabs.com/v1
  properties:
  - url: https://docs.wellsaidlabs.com/reference/available-voice-avatars
    type: Documentation
  - url: https://docs.wellsaidlabs.com/reference
    type: APIReference
  - url: openapi/wellsaid-openapi.yml
    type: OpenAPI
  - url: collections/wellsaid.postman_collection.json
    type: PostmanCollection
  - url: collections/wellsaid.opencollection.json
    type: OpenCollection
  description: List available voice avatars (GET /tts/avatars) with their speaker_id,
    name, accent, and speaking style for selecting a voice, plus respelling suggestions
    and replacement libraries that shape pronunciation across renders.
common:
- type: GitHubOrganization
  url: https://github.com/wellsaid-labs
- type: LinkedIn
  url: https://www.linkedin.com/company/wellsaid-labs
- type: Website
  url: https://wellsaidlabs.com
- type: Documentation
  url: https://docs.wellsaidlabs.com
- type: Plans
  url: plans/wellsaid-plans-pricing.yml
- type: RateLimits
  url: rate-limits/wellsaid-rate-limits.yml
- type: FinOps
  url: finops/wellsaid-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com