Audio filters & mixers
Clean up the user's audio before it reaches VAD and speech-to-text, and mix background sound into the bot's audio.
An audio filter cleans up the user's audio before it reaches VAD and speech-to-text (set it as audioInFilter in the transport's params). An audio mixer blends background sound into the bot's audio (audioOutMixer).
| Provider | Classes | Package | Status |
|---|---|---|---|
| RNNoise filter | RNNoiseFilter | @pipedog/audio-rnnoise-filter | Ported |
| Soundfile mixer | SoundfileMixer | @pipedog/audio-soundfile-mixer | Ported |
| Ducking | AudioDuckingFilter, AudioDuckingObserver | @pipedog/audio-ducking | pipedog only |
| TEN VAD | TenVADAnalyzer | @pipedog/audio-ten-vad | pipedog only |
| ai-coustics | AICFilter, AICQuailVADAnalyzer | Deferred | |
| Koala | KoalaFilter | Deferred | |
| Krisp VIVA | KrispVivaFilter, KrispVivaVadAnalyzer, KrispVivaTurn | Deferred |
Pipecat's audio filters & mixers reference lists every upstream provider. Those not in this table are on Other upstream providers.
pipedog is an unofficial community TypeScript port of Pipecat. It is not affiliated with or endorsed by Daily or the Pipecat project.
Portions adapted from the Pipecat documentation, Copyright (c) 2024–2025 Daily, BSD-2-Clause (see apps/docs/LICENSE-pipecat-docs).