Everything you need to build with VocaSync — text-to-speech synthesis, forced alignment, transcription, and translation. New here? Start with Getting started, or jump to a section below. Building an integration? See the API reference.

Introduction

Getting started
Create an account, claim your free tier, run your first project, and tour the dashboard.

Core services

Speech synthesis
Turn text into studio-quality speech — voices, quality tiers, output formats, pronunciation maps, and chunking.
Forced alignment
Deterministic word-level timestamps from your own transcript — JSON, SRT, and WebVTT output.
Transcription
WhisperX speech-to-text across 99+ languages, with transcript review before a linked alignment.
Translation
Neural machine translation with optional AI refinement, tonal registers, and subtitle readability limits.

Workflows

Subtitling
Transcription → alignment → translation in one bundle, with optional transcript review and upfront pricing.
Dub-Prep
Synthesis → alignment in one bundle — generate narration and get word-level timings for dubbing.

Developers

API keys & authentication
Create keys, authenticate requests, and drive every VocaSync service from your own code.
Webhooks
Subscribe to job and pipeline events, filter what you receive, and verify signatures.
Publishable keys
Share artifacts publicly with scoped, revocable keys — no API secret exposure.
Integrations
Official plugins for Astro and WordPress, plus building your own integration.

Account & billing

Projects
How projects and jobs progress, what artifacts they produce, and how to download them.
Billing & credits
Pay-as-you-go top-ups, the free tier, usage tracking, and volume pricing.
Account & notifications
Passkeys and sessions, notification preferences, and support tickets.

Reference

Glossary
Plain-language definitions of the terms used across VocaSync and these docs.
Troubleshooting
Fixes for the problems people hit most — failed jobs, language mismatches, low balance, and webhooks.