WellSaid Labs
WellSaid Labs is an AI text-to-speech (TTS) platform that turns text into studio-quality synthetic voiceover using a library of 200+ AI voice avatars across many styles, languages, and accents. Beyond the AI Voice Studio web app, WellSaid exposes a documented REST API (base https://api.wellsaidlabs.com/v1) that renders text to speech, streams audio for low time-to-first-byte playback, returns word-level timing and subtitles, manages asynchronous clips, lists voice avatars, and lets teams control pronunciation with replacement libraries and respelling suggestions. The API authenticates with an X-Api-Key header and is gated behind a trial API key and a business plan.
APIs
WellSaid Labs Text-to-Speech API
Render text to speech and receive the audio as an HTTP stream for low time-to-first-byte playback, or render with word-level timing and subtitle output. Requests take the text, ...
WellSaid Labs Clips API
Create text-to-speech clips asynchronously, list recent clips, fetch a single clip by id, and combine a list of clips into a single audio file with pauses between them. Useful f...
WellSaid Labs Voice Avatars API
List the available voice avatars with their metadata - the numeric speaker id, avatar name, style (Narration, Promo, Conversational, Character), language, accent, descriptive ch...
WellSaid Labs Pronunciation API
Manage pronunciation across renders. Create and manage replacement libraries and the individual replacements inside them so brand names, acronyms, and jargon are spoken consiste...