Microphone_input, endpointing_config = PunctuationEndpointingConfig() Streaming = True, use_default_devices = FalseĭeepgramTranscriberConfig. Microphone_input, speaker_output = create_microphone_input_and_speaker_output( deepgram_transcriber import DeepgramTranscriber # these can also be set as environment variables vocode. azure_synthesizer import AzureSynthesizer from vocode. synthesizer import AzureSynthesizerConfig from vocode. agent import ChatGPTAgentConfig from vocode. chat_gpt_agent import ChatGPTAgent from vocode. helpers import create_microphone_input_and_speaker_output from vocode. streaming_conversation import StreamingConversation from vocode. Import asyncio import signal import vocode from vocode. And we'd love to talk to you on Discord! □ Quickstart (Self-hosted) More guides for this coming soon!īecause our StreamingConversation runs locally, it's relatively quick to develop on! Feel free to fork and create a PR and we will get it merged as soon as possible. You can also work with our BaseInputDevice and BaseOutputDevice abstractions to set up voice applications on new surfaces/platforms. You can extend our BaseAgent, BaseTranscriber, and BaseSynthesizer abstractions to integrate with new LLM APIs, speech recognition and speech synthesis providers. We'd love for you all to build on top of our abstractions to enable new and better LLM voice applications! □ ➡️ Send out phone calls from your phone number managed by an LLM-based agentĬheck out our React SDK here! □ Contribution.➡️ □ Set up a phone number that responds with a LLM-based agent.□ Spin up a conversation with your system audio.Vocode provides easy abstractions and integrations so that everything you need is in a single library. You can also build personal assistants or apps like voice-based chess. Using Vocode, you can build real-time streaming conversations with LLMs and deploy them to phone calls, Zoom meetings, and more. Vocode is an open source library that makes it easy to build voice-based LLM apps. If you have multiple Media Centers or renderers, you can POST a JSON body to that url with specific parameters to select the proper host and renderer.Community | Docs | Dashboard vocode Build voice-based LLM apps in minutes
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |