Voice & Audio Application Developers
Speech-to-text and text-to-speech as a real API, not a demo that falls over past a sentence.
Who this is for
Voice UI Developers
Build voice-first user interfaces — builds voice-controlled apps, multimodal interfaces.
Speech Developers
Work with speech recognition — builds transcription, voice commands.
TTS Developers
Work with text-to-speech — builds audiobooks, voice assistants.
Audiobook Developers
Build audiobook platforms — builds voice-controlled audiobooks.
Podcast Developers
Build podcast platforms — builds voice-controlled podcast playback.
Example use case
A developer builds a voice-controlled audiobook app using BotSurf's API, combining speech recognition and text-to-speech the same way multi-provider voice SDKs chain ASR, an LLM, and TTS together \u2014 except here it's one API rather than three separate providers to integrate and keep in sync.
Get an API key
Free to start, usage-based pricing when you ship, or hold BOT for API access with no separate subscription.