API Documentation
Complete reference for integrating VoiceMaker speech AI into your applications. These docs cover authentication, all API endpoints, webhooks, error handling, and SDK usage — built for Nigerian languages: Yoruba, Igbo, Hausa, Nigerian Pidgin, and English.
Version 1.0 · 2026
What you can build
VoiceMaker exposes four speech and language modules over a single REST API:
- Transcription (ASR) — convert audio files to text with automatic language detection.
- Text-to-Speech (TTS) — generate natural, dialect-accurate speech from text.
- Animate — produce lip-synced talking-head videos from an image and audio.
- Explain (LLM) — explain, summarize, translate, and simplify text. Coming soon
Base URL
All API requests are made to:
https://api.myvoicemaker.ai/dev/v1
Every response is JSON and includes a requestId for support and debugging.
Next steps
- New here? Start with the Quick Start to make your first request.
- Learn the Key Concepts behind modules, jobs, and credits.
- Generate a key and secure your calls in Authentication.
- Prefer a client library? See the SDKs & Libraries.