SLNG provides real-time speech and language APIs with consistent HTTP and WebSocket interfaces across providers. Use the cards below to jump into the detailed reference for each capability.
Text-to-Speech
HTTP & WebSocket
Turn text into audio with low-latency neural voices over HTTP or WebSocket.
Speech-to-Text
Streaming & batch
Transcribe speech in real time or batch with language, diarization, and confidence controls.
Voice Agents
Calls & orchestration
Spin up voice agents that combine STT, LLM, and TTS with webhooks and call dispatch.
Last modified on