Core Modules
VoiceMaker bundles four speech and language capabilities behind one API and one set of credentials.
Transcription (ASR)
Automatic Speech Recognition. Transcribe audio files to text in Yoruba, Igbo, Hausa, Nigerian Pidgin, and Nigerian English, with optional automatic language detection. Runs asynchronously — submit a job, then poll or receive a webhook.
→ Transcription (ASR) reference
Text-to-Speech (TTS)
Generate natural, dialect-accurate speech from text across multiple voice personas and styles. Returns a downloadable audio URL synchronously.
→ Text-to-Speech (TTS) reference
Animate
Generate lip-synced talking-head videos by combining a portrait image with an audio clip. Runs asynchronously and returns a video URL on completion.
Explain (LLM)
Generate explanations, summaries, translations, and simplifications of text in supported Nigerian languages. Returns the processed text synchronously.