Deepgram Stt Livekit Documentation Deepgram speech to text is available in livekit agents through livekit inference and the deepgram plugin. with livekit inference, your agent runs on livekit's infrastructure to minimize latency. no separate provider api key is required, and usage and rate limits are managed through livekit cloud. This guide walks you through building a voice ai agent that uses livekit agents for real time audio transport and deepgram for speech to text (stt) and text to speech (tts).
Enterprise Voice Ai Stt Tts Agent Apis Deepgram Speech to text providers relevant source files purpose and scope this page documents the speech to text (stt) provider plugin system in the livekit agents framework. stt providers convert audio streams into text transcriptions, supporting both real time streaming transcription and batch recognition. If you’d like to dive deeper or explore more customization options, i highly recommend checking out the deepgram plugin guide and the custom stt node documentation. Args: model: the deepgram model to use for speech recognition. defaults to "nova 3". language: the language code for recognition. defaults to "en us". detect language: whether to enable automatic language detection. defaults to false. interim results: whether to return interim (non final) transcription results. Support for deepgram 's voice ai services in livekit agents. more information is available in the docs for the stt and tts integrations. you'll need an api key from deepgram. it can be set as an environment variable: deepgram api key. agent framework plugin for services using deepgram's api.
Enterprise Voice Ai Stt Tts Agent Apis Deepgram Args: model: the deepgram model to use for speech recognition. defaults to "nova 3". language: the language code for recognition. defaults to "en us". detect language: whether to enable automatic language detection. defaults to false. interim results: whether to return interim (non final) transcription results. Support for deepgram 's voice ai services in livekit agents. more information is available in the docs for the stt and tts integrations. you'll need an api key from deepgram. it can be set as an environment variable: deepgram api key. agent framework plugin for services using deepgram's api. Learn how to build a production ready python voice agent using livekit agents. covers stt, llm, tts integration, local testing, and deployment. We welcome and appreciate contributions of any kind, be it feedback, bugfixes, features, new plugins and tools, or better documentation. you can file issues under this repo, open a pr, or chat with us in livekit's slack community. Celloip builds production grade ai voice agents using the livekit agents sdk. our stt→llm→tts pipeline integrates with deepgram, gpt 4o, claude, elevenlabs, and cartesia. achieve sub 500ms latency, sip trunk integration for inbound pstn calls, 100% open source design, and support for 10 ai providers. self hosted on premise with python sdk and mcp tool support. In this tutorial, you will learn how to build a real time ai chatbot with vision and voice capabilities using openai, livekit and deepgram deployed on digitalocean gpu droplets.
Comments are closed.