Overview
Build with TaskInfer's available audio APIs and understand each request lifecycle.
TaskInfer provides focused APIs for audio processing. Start with one shared account and authentication setup, then choose the guide for the capability your application needs.
Available capabilities
- Speech to Text transcribes uploaded files or public HTTPS audio URLs.
- Speaker Diarization adds speaker turns to verbose transcription output.
- Audio Separation separates dialogue, music, and effects through an asynchronous task.
- Text to Speech is coming soon.
Request lifecycles
Speech to Text returns its result in the request response. Audio Separation creates a task that moves through queued, in_progress, completed, or failed; poll the task until it reaches a terminal state.
Start building
- Complete Get started to prepare a workspace, API key, and credits.
- Open the guide for the capability you want to integrate.
- Use the API Reference for endpoint and request definitions.