Picovoice Wordmark
Start Building
Introduction
Introduction
AndroidC.NETiOSLinuxmacOSNode.jsPythonRaspberry PiWebWindows
AndroidC.NETiOSNode.jsPythonWeb
SummaryPicovoice picoLLMGPTQ
Introduction
AndroidC.NETFlutteriOSJavaLinuxmacOSNode.jsPythonRaspberry PiReactReact NativeWebWindows
AndroidC.NETFlutteriOSJavaNode.jsPythonReactReact NativeWeb
SummaryPicovoice LeopardAmazon TranscribeAzure Speech-to-TextGoogle ASRGoogle ASR (Enhanced)IBM Watson Speech-to-TextWhisper Speech-to-Text
FAQ
Introduction
AndroidC.NETFlutteriOSJavaLinuxmacOSNode.jsPythonRaspberry PiReactReact NativeWebWindows
AndroidC.NETFlutteriOSJavaNode.jsPythonReactReact NativeWeb
SummaryPicovoice CheetahAzure Real-Time Speech-to-TextAmazon Transcribe StreamingGoogle Streaming ASR
FAQ
Introduction
AndroidC.NETiOSLinuxmacOSNode.jsPythonRaspberry PiWebWindows
AndroidC.NETiOSNode.jsPythonWeb
SummaryAmazon PollyAzure TTSElevenLabsOpenAI TTSPicovoice Orca
Introduction
AndroidCiOSLinuxmacOSPythonRaspberry PiWebWindows
AndroidCiOSPythonWeb
SummaryPicovoice KoalaMozilla RNNoise
Introduction
AndroidCiOSLinuxmacOSNode.jsPythonRaspberry PiWebWindows
AndroidCNode.jsPythoniOSWeb
SummaryPicovoice EaglepyannoteSpeechBrainWeSpeaker
Introduction
AndroidCiOSLinuxmacOSPythonRaspberry PiWebWindows
AndroidCiOSPythonWeb
SummaryPicovoice FalconAmazon TranscribeAzure Speech-to-TextGoogle Speech-to-Textpyannote
Introduction
AndroidArduinoCChrome.NETEdgeFirefoxFlutteriOSJavaLinuxmacOSMicrocontrollerNode.jsPythonRaspberry PiReactReact NativeSafariWebWindows
AndroidC.NETFlutteriOSJavaMicrocontrollerNode.jsPythonReactReact NativeWeb
SummaryPicovoice PorcupineSnowboyPocketSphinx
Wake Word TipsFAQ
Introduction
AndroidArduinoCChrome.NETEdgeFirefoxFlutteriOSJavaLinuxmacOSMicrocontrollerNode.jsPythonRaspberry PiReactReact NativeSafariWebWindows
AndroidC.NETFlutteriOSJavaMicrocontrollerNode.jsPythonReactReact NativeWeb
SummaryPicovoice RhinoGoogle DialogflowAmazon LexIBM WatsonMicrosoft LUIS
Expression SyntaxFAQ
Introduction
AndroidArduinoC.NETiOSLinuxmacOSMicrocontrollerNode.jsPythonRaspberry PiWebWindows
AndroidC.NETiOSMicrocontrollerNode.jsPythonWeb
SummaryPicovoice CobraWebRTC VADSilero VAD
FAQ
Introduction
AndroidC.NETFlutteriOSNode.jsPythonReact NativeWeb
AndroidC.NETFlutteriOSNode.jsPythonReact NativeWeb
Introduction
C.NETNode.jsPython
C.NETNode.jsPython
FAQGlossary

Cobra Voice Activity Detection
Python API

API Reference for the Cobra Python SDK (PyPI).


pvcobra.create()

def create(
access_key: str,
device: str,
library_path: Optional[str] = None) -> Cobra

Factory method for the Cobra voice activity detection (VAD) engine.

Parameters

  • access_key str : AccessKey obtained from Picovoice Console.
  • library_path Optional[str] : Absolute path to Cobra's dynamic library. If not set, it will be set to the default location.
  • device Optional[str] : String representation of the device (e.g., CPU or GPU) to use. If set to best, the most suitable device is selected automatically. If set to gpu, the engine uses the first available GPU device. To select a specific GPU device, set this argument to gpu:${GPU_INDEX}, where ${GPU_INDEX} is the index of the target GPU. If set to cpu, the engine will run on the CPU with the default number of threads. To specify the number of threads, set this argument to cpu:${NUM_THREADS}, where ${NUM_THREADS} is the desired number of threads.

Returns

  • Cobra : An instance of Cobra VAD engine.

pvcobra.available_devices()

def available_devices(library_path: Optional[str] = None) -> Sequence[str]

Lists all available devices that Cobra can use for inference. Each entry in the list can be the device argument of create() factory method or Cobra constructor.

Parameters

  • library_path Optional[str] : Absolute path to Cobra's dynamic library. If not set it will be set to the default location.

Returns

  • Sequence[str]: List of all available devices that Cobra can use for inference.

Throws

  • CobraError

pvcobra.Cobra

class Cobra(object)

Class for the Cobra VAD engine. Cobra can be initialized either using the module level create() function or directly using the class __init__() method. Resources should be cleaned when you are done using the delete() method.


pvcobra.Cobra.frame_length

self.frame_length: int

The number of audio samples per frame that Cobra accepts.


pvcobra.Cobra.sample_rate

self.sample_rate: int

The audio sample rate the Cobra accepts.


pvcobra.Cobra.version

self.version: str

The Cobra library version string.


pvcobra.Cobra.__init__()

def __init__(
self,
access_key: str,
device: str,
library_path: str) -> Cobra

__init__ method for Cobra VAD engine.

Parameters

  • access_key str : AccessKey obtained from Picovoice Console.
  • library_path str : Absolute path to Cobra's dynamic library.
  • device str : String representation of the device (e.g., CPU or GPU) to use. If set to best, the most suitable device is selected automatically. If set to gpu, the engine uses the first available GPU device. To select a specific GPU device, set this argument to gpu:${GPU_INDEX}, where ${GPU_INDEX} is the index of the target GPU. If set to cpu, the engine will run on the CPU with the default number of threads. To specify the number of threads, set this argument to cpu:${NUM_THREADS}, where ${NUM_THREADS} is the desired number of threads.

Returns

  • Cobra : An instance of Cobra VAD engine.

Throws

  • CobraError

pvcobra.Cobra.delete()

def delete(self)

Releases resources acquired by Cobra.


pvcobra.Cobra.process()

def process(self, pcm: List[int]) -> float

Processes a frame of the incoming audio stream and emits the detection result. The required number of samples-per-frame can be obtained by calling .frame_length. The incoming audio needs to have a sample rate equal to .sample_rate and be 16-bit linearly-encoded. Cobra operates on single-channel audio.

Parameters

  • pcm List[int] : A frame of audio samples.

Returns

  • float : Probability of voice activity. It is a floating-point number within [0, 1].

Throws

  • CobraError

pvcobra.CobraError

class CobraError(Exception)

Error thrown if an error occurs within Cobra VAD engine.

Exceptions

class CobraActivationError(CobraError)
class CobraActivationLimitError(CobraError)
class CobraActivationRefusedError(CobraError)
class CobraActivationThrottledError(CobraError)
class CobraIOError(CobraError)
class CobraInvalidArgumentError(CobraError)
class CobraInvalidStateError(CobraError)
class CobraKeyError(CobraError)
class CobraMemoryError(CobraError)
class CobraRuntimeError(CobraError)
class CobraStopIterationError(CobraError)

Was this doc helpful?

Issue with this doc?

Report a GitHub Issue
Cobra Voice Activity Detection Python API
  • pvcobra.create()
  • pvcobra.available_devices()
  • pvcobra.Cobra
  • frame_length
  • sample_rate
  • version
  • __init__()
  • delete()
  • process()
  • pvcobra.CobraError
Voice AI
  • picoLLM On-Device LLM
  • Leopard Speech-to-Text
  • Cheetah Streaming Speech-to-Text
  • Orca Text-to-Speech
  • Koala Noise Suppression
  • Eagle Speaker Recognition
  • Falcon Speaker Diarization
  • Porcupine Wake Word
  • Rhino Speech-to-Intent
  • Cobra Voice Activity Detection
Resources
  • Docs
  • Console
  • Blog
  • Use Cases
  • Playground
Sales & Services
  • Consulting
  • Foundation Plan
  • Enterprise Plan
  • Enterprise Support
Company
  • About us
  • Careers
Follow Picovoice
  • LinkedIn
  • GitHub
  • X
  • YouTube
  • AngelList
Subscribe to our newsletter
Terms of Use
Privacy Policy
© 2019-2025 Picovoice Inc.