Voxta docs
Voxta ServerServices

Speech-to-Text

Voice transcription providers — turn your microphone input into text the AI can read.

STT services transcribe what you speak into text that Voxta feeds to the LLM. Voxta Cloud also provides STT — see its docs.

Cloud-Based

AssemblyAI

Well-known online speech recognition.

Azure Speech Service

Microsoft Azure Cognitive Services STT (also offers TTS).

Deepgram

Low-latency cloud STT.

Self-Hosted: Zero-Setup

Vosk

Open-source offline STT, multilingual.

Whisper Live

Open-source neural STT based on Whisper.

Windows Speech

Built-in Windows STT (basic quality, free, offline).

Remote TTS (HTTP API)

Bring your own TTS by exposing it over Voxta's simple HTTP contract.

AssemblyAI

Cloud speech-to-text service.

On this page

Cloud-BasedSelf-Hosted: Zero-Setup