| Library | Details | Docs |
|---|---|---|
| audio-codec-tlv320dac3100 | This is the driver library supporting a Texas Instruments TLV320DAC3100
low-power stereo audio DAC with audio processing on PSOC™
Edge E84 Evaluation Kit (KIT_PSE84_EVAL_EPC2,
KIT_PSE84_EVAL_EPC4). |
API reference |
| audio-front-end | This is an agnostic audio processing technology for more accurate voice command recognition (far-field or close field) by removing interfering sounds captured from the microphone. | API reference |
| audio-sw-codecs | This implements an abstraction layer to a audio software codec. It abstracts multiple audio codecs that help applications to have an unified interface across the various software codec. | API reference |
| audio-voice-core | This consists of core audio algorithm implementation. It contains core algorithm implementation for speech-onset-detection, low-power wake word detection, and audio front-end. | README |
| speech-onset-detection | This is used to detect the beginning of a spoken word or utterance. For the target application, this is the first stage of a low power multi-stage wake-up phrase solution. | API reference |
| staged-voice-control | Staged voice control middleware provides easy to use API on core1 to feed the audio data, get notified about current stage in the audio pipeline. On core2, it provides simple to use API to get the data from core1 and sending the notification about stage change to core1. | API reference |
| voice-assistant | The DEEPCRAFT voice assistant is a Edge AI software product used to create and deploy voice assistants (Wake Word Detection + Natural Language Understanding) into an embedded environment. | Code example |
ModusToolbox™ for Audio
Last updated on