Speech To Speech Python Packages

vakforge

The decision layer for open voice AI. Turns the data a company already has into a self-hosted voice assistant and tells you what actually needs training, usually less than you think.

voice-prices

Open price database for voice AI APIs - STT, LLM, TTS, S2S, VAD

tring

Open-source voice agent stack: one agent contract, any runtime (cascade / speech-to-speech / hybrid), local-first, cost-transparent.

mlx-audio-plus

Python tools for text to speech (TTS), speech to text (STT), and speech to speech (STS) powered by MLX

dograh-sdk

Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.

pipecat-thunderphone

ThunderPhone voice agents as a Pipecat speech-to-speech service (pipecat-thunderphone on PyPI)

vox-serve

A Streaming-Native Serving Engine for TTS/STS Models

llama-jarvis

Turn any LLM into Jarvis