Extensions
This section provides information about the currently available Switchboard SDK extensions.
Do you want your technology to be a Node in Switchboard?
We can help you creating an extension and show it on this page.
Get in touch at hello@synervoz.com.
Voice
- Bose PinPoint: Removes any unwanted noise from an audio signal.
- RNNoise: Noise suppression library based on a recurrent neural network.
- Speex DSP: Echo cancellation and voice signal pre-processing.
- Voice Effects: Real-time voice changer effects.
- Silero Voice Activity Detector: AI-based real-time speech detection.
- Silero Text-to-Speech: AI-based real-time text-to-speech solution.
- Silero Speech-to-Text: AI-based real-time speech-to-text solution.
- Picovoice Speech-to-Text: AI-based on device real-time speech-to-text solution.
- Voicemod: Realtime sound effects.
Communications
- WebRTC: Using the WebRTC framework with custom input and output audio devices.
- Agora: Easy audio integration with Agora's voice and video SDKs.
- TokBox: Easy audio integration with the TokBox communications SDK.
- Amazon Chime: Using the Amazon Chime SDK with custom input and output audio devices.
- Amazon IVS: Live audio and video streaming service with both low-latency and real-time streaming capabilities.
- LiveKit: Open-source platform that provides scalable, real-time audio and video streaming capabilities.
Music
- Music Synchronization: Synchronizing audio players over the internet.
- Spotify: Streaming music from Spotify.
- Dash Radio: Streaming music from Dash radio.
- ExoPlayer: Tap into the extensive capabilities of ExoPlayer.
- AudioShake: AI-based real-time on device music stem separation.
- Aubio: Real-time audio analysis capabilities like pitch detection.
DSP
- Superpowered: Provides high-quality low-latency audio DSP components.
- SoX: A collection of free to use audio effects.
- VST: Real-time audio processing with VST3 plug-ins
Machine Learning
- RTNeural: Running RTNeural machine learning models for audio processing.
- TensorFlow: Running TensorFlow machine learning models for audio processing.
- ONNX: Running ONNX machine learning models for audio processing.
- PyTorch: Running PyTorch machine learning models for audio processing.
- Whisper: Whisper based speech-to-text
- Sherpa: Sherpa based speech-to-text
Do you want your technology to be a Node in Switchboard?
We can help you creating an extension and show it on this page.
Get in touch at hello@synervoz.com.