AI Audio API

AI music API, speech synthesis and transcription

Generate and extend music, separate vocals, synthesize speech, or transcribe audio. Compare Suno, ElevenLabs, Gemini TTS and transcription models below; each model has its own API examples, rates and reference documentation.

Choose a model for your workflow

Compare supported operations, output specifications, and credit units before integrating. The model’s documentation lists request fields and limits. Multimodal models can appear in more than one category while sharing one canonical API page.

Integrate with one VezAPI key

Create your account, choose a credit pack, and follow the model’s request example. Asynchronous models return a task ID; use polling or callbacks to retrieve the result. Chat models use their documented streaming protocol.