voiceagent

package

v0.68.6 Latest Latest Go to latest Published: Sep 3, 2026 License: Apache-2.0 Imports: 3 Imported by: 0

Details

Valid go.mod file
Redistributable license
Tagged version
Stable version
Learn more about best practices

Repository

github.com/kombifyio/SpeechKit

Links

Open Source Insights

Documentation ¶

Overview ¶

Package voiceagent provides an embeddable Voice Agent service.

Voice Agent is the realtime audio-to-audio mode: a duplex WebSocket session with the underlying live model (Gemini Live, OpenAI Realtime, or a pipeline fallback) where the user and the agent take audio turns in sequence. Use this when the host needs brainstorming, support, or follow-up dialogue rather than a one-shot result.

For tool registration, lifecycle hooks, and session memory, build on top of this with github.com/kombifyio/SpeechKit/pkg/speechkit/agentkit.

Construct an instance with NewService, passing a provider and the strict- mode policy fields from the host config.

Index ¶

Variables
type Callbacks
type Config
type Options
type Provider
type Service
- func NewService(opts Options) (*Service, error)

Constants ¶

This section is empty.

Variables ¶

View Source

var ErrMissingProvider = errors.New("speechkit voiceagent: provider is required")

Functions ¶

This section is empty.

Types ¶

type Callbacks ¶

type Callbacks struct {
	OnAudio func([]byte)
	OnText  func(string)
	OnError func(error)
}

type Config ¶

type Config struct {
	ProviderProfileID string
	Model             string
	Locale            string
	Instruction       string
}

type Options ¶

type Options struct {
	Config    Config
	Callbacks Callbacks
	Provider  Provider
}

type Provider ¶

type Provider interface {
	StartVoiceAgent(context.Context, Config, Callbacks) error
	StopVoiceAgent(context.Context) (speechkit.VoiceAgentSession, error)
	SendText(context.Context, string) error
	CurrentSession(context.Context) (speechkit.VoiceAgentSession, error)
}

type Service ¶

type Service struct {
	// contains filtered or unexported fields
}

func NewService ¶

func NewService(opts Options) (*Service, error)

func (*Service) CurrentSession ¶

func (s *Service) CurrentSession(ctx context.Context) (speechkit.VoiceAgentSession, error)

func (*Service) SendText ¶

func (s *Service) SendText(ctx context.Context, text string) error

func (*Service) Start ¶

func (s *Service) Start(ctx context.Context) error

func (*Service) Stop ¶

func (s *Service) Stop(ctx context.Context) (speechkit.VoiceAgentSession, error)

Source Files ¶

View all Source files

service.go

Directories ¶

Path	Synopsis
a2a Package a2a adapts a registered A2A agent to SpeechKit's cascaded voice pipeline.	Package a2a adapts a registered A2A agent to SpeechKit's cascaded voice pipeline.
cascaded Package cascaded implements a turn-based STT -> LLM -> TTS voice agent provider.	Package cascaded implements a turn-based STT -> LLM -> TTS voice agent provider.
live Package live exposes the low-level Voice Agent realtime-protocol types.	Package live exposes the low-level Voice Agent realtime-protocol types.
allproviders
assemblyai
deepgram
foundry Package foundry adapts the OpenAI Realtime provider to Microsoft Foundry.	Package foundry adapts the OpenAI Realtime provider to Microsoft Foundry.
gemini
livecontract Package livecontract provides reusable conformance checks for LiveProvider implementations.	Package livecontract provides reusable conformance checks for LiveProvider implementations.
openai
local Package local implements voiceagent.Provider on top of an in-process live session — realtime voice agents (Deepgram Voice Agent, Gemini Live, OpenAI Realtime, AssemblyAI, cascaded) without a speechkit-server.	Package local implements voiceagent.Provider on top of an in-process live session — realtime voice agents (Deepgram Voice Agent, Gemini Live, OpenAI Realtime, AssemblyAI, cascaded) without a speechkit-server.

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL