stt

type AssemblyAIProvider struct {
	APIKey           string
	Models           []string
	StreamingModel   string
	BaseURL          string
	StreamingBaseURL string
	// SyncBaseURL points at the synchronous transcription endpoint
	// (https://sync.assemblyai.com; regional variants sync.us / sync.eu
	// exist). The Sync API returns a finished Universal-3.5 Pro transcript
	// in one request/response (~134 ms p50) for clips up to 120 s / 40 MB —
	// the low-latency dictation path. Empty uses the global endpoint.
	SyncBaseURL string
	// SyncModel is the X-AAI-Model routing header value for sync requests.
	// Empty uses universal-3-5-pro.
	SyncModel string
	// DisableSync forces every transcription through the classic async
	// upload+poll flow, even for clips the Sync API could serve.
	DisableSync bool
	// StreamingLLM, when set, attaches AssemblyAI LLM Gateway to Universal-3.5
	// Pro realtime turns. The formatted transcript still arrives as Turn;
	// LLMGatewayResponse may rewrite the final text for live cleanup.
	StreamingLLM *AssemblyAIStreamingLLM
	Validation   netsec.ValidationOptions
	PollInterval time.Duration
	PollTimeout  time.Duration
	// contains filtered or unexported fields
}

type AssemblyAIStreamingLLM struct {
	Model     string
	Prompt    string
	MaxTokens int
}

type CapabilityReporter interface {
	Capabilities() []speechkit.Capability
}

type DeepgramOptions struct {
	Configured            bool
	SmartFormat           bool
	Dictation             bool
	FillerWords           bool
	Numerals              bool
	DetectLanguage        bool
	LanguageOverride      string
	UseVocabularyKeyterms bool
	Keyterms              []string
	EndpointingMs         int
}

type DeepgramProvider struct {
	APIKey                string
	Model                 string
	DiarizationModel      string
	BaseURL               string
	Validation            netsec.ValidationOptions
	SmartFormat           bool
	Dictation             bool
	FillerWords           bool
	Numerals              bool
	DetectLanguage        bool
	LanguageOverride      string
	UseVocabularyKeyterms bool
	Keyterms              []string
	EndpointingMs         int
	// contains filtered or unexported fields
}

type FluxStreamOptions struct {
	// Model selects flux-general-en or flux-general-multi. Empty uses the
	// multilingual model, which is the point of Flux for SpeechKit: it detects
	// and switches languages within a single conversation.
	Model string
	// LanguageHints biases recognition toward the given BCP-47 languages. Only
	// flux-general-multi accepts hints; they narrow the model, they do not pin
	// it, and every turn still reports what it actually heard.
	LanguageHints []string
	// Keyterms boost domain vocabulary (product names and other terms the model
	// has not seen).
	Keyterms []string
	// EOTThreshold, EagerEOTThreshold, and EOTTimeoutMs tune turn detection.
	// Zero keeps Deepgram's defaults; out-of-range values are clamped.
	EOTThreshold      float64
	EagerEOTThreshold float64
	EOTTimeoutMs      int
}

type FluxTurn struct {
	// Event is one of the Flux lifecycle events above.
	Event string `json:"event"`
	// TurnIndex counts turns within the connection.
	TurnIndex int `json:"turnIndex"`
	// Transcript is the full turn transcript so far, not a delta.
	Transcript string     `json:"transcript"`
	Words      []FluxWord `json:"words,omitempty"`
	// Languages are the languages actually detected in this turn; empty when
	// the turn holds no speech yet.
	Languages []string `json:"languages,omitempty"`
	// EndOfTurnConfidence is the model's confidence that the speaker is done.
	EndOfTurnConfidence float64 `json:"endOfTurnConfidence"`
	// AudioWindowStartMs/EndMs bound the audio this turn covers.
	AudioWindowStartMs int64 `json:"audioWindowStartMs"`
	AudioWindowEndMs   int64 `json:"audioWindowEndMs"`
	// SequenceID is Deepgram's per-connection event counter.
	SequenceID int64 `json:"sequenceId"`
	// RequestID identifies the connection in Deepgram's logs.
	RequestID string `json:"requestId"`
	// LatencyMs is the time from stream open to this event.
	LatencyMs int64 `json:"latencyMs"`
}

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

type FluxWord struct {
	Text       string  `json:"text"`
	Confidence float64 `json:"confidence"`
	StartMs    int64   `json:"startMs"`
	EndMs      int64   `json:"endMs"`
}

type GoogleSTTProvider struct {
	APIKey                    string
	Model                     string // "latest_long", "latest_short", or another Google STT v1 model tag
	STTCredentialsJSONEnv     string
	ApplicationCredentialsEnv string
	BaseURL                   string // Override for testing; defaults to googleSTTBaseURL
	Validation                netsec.ValidationOptions
	// contains filtered or unexported fields
}

type HuggingFaceProvider struct {
	Model      string
	Token      string
	BaseURL    string // Override for testing; defaults to hfBaseURL
	Validation netsec.ValidationOptions
	// contains filtered or unexported fields
}

type InstallStatus struct {
	BinaryFound bool     `json:"binaryFound"`
	BinaryPath  string   `json:"binaryPath"`
	ModelFound  bool     `json:"modelFound"`
	ModelPath   string   `json:"modelPath"`
	ModelBytes  int64    `json:"modelBytes"`
	ServerReady bool     `json:"serverReady"`
	Problems    []string `json:"problems,omitempty"`
}

type LocalProvider struct {
	BaseURL    string // e.g. "http://127.0.0.1:8080"
	Port       int
	ModelPath  string
	GPU        string
	Validation netsec.ValidationOptions
	// contains filtered or unexported fields
}

type OpenAICompatibleProvider struct {
	BaseURL    string
	APIKey     string
	Model      string
	Validation netsec.ValidationOptions
	// contains filtered or unexported fields
}

type OpenRouterSTTProvider struct {
	BaseURL    string
	APIKey     string
	Model      string
	Validation netsec.ValidationOptions
	// contains filtered or unexported fields
}

type ResolvedTranscribeOptions struct {
	Language              string
	Model                 string
	Prompt                string
	ContextPrompt         string
	LanguageHints         []string
	Keyterms              []string
	Speaker               speaker.Options
	DetectLanguage        bool
	Punctuation           bool
	SmartFormat           bool
	Dictation             bool
	FillerWords           bool
	Numerals              bool
	UseVocabularyKeyterms bool
	Timestamps            bool
	EndpointingMs         int
	PrivacyRedaction      bool
	VoiceFocus            bool
	MedicalDomain         bool
	Effective             provideropts.EffectiveOptions
}

type Result struct {
	Text       string
	Language   string
	Duration   time.Duration
	Provider   string
	Model      string
	Confidence float64 // If available from the provider
	// Words carries per-word acoustic confidence when the provider exposes it.
	// nil for providers without word-level confidence. Offsets are NOT tracked
	// because downstream vocabulary/punctuation rewriting invalidates them;
	// consumers match on the word text instead.
	Words    []WordConfidence
	Speakers *speaker.DiarizationResult
}

type STTProvider interface {
	// Transcribe sends audio data to the STT backend and returns the transcription.
	Transcribe(ctx context.Context, audio []byte, opts TranscribeOpts) (*Result, error)

	// Name returns the provider identifier (e.g. "local", "vps", "huggingface").
	Name() string

	// Health checks if the provider is reachable and ready.
	Health(ctx context.Context) error
}

type TranscribeOpts struct {
	Language string   // "de", "en", "auto"; request override only
	Model    string   // Optional: model override
	Prompt   string   // Optional: provider-specific hint prompt for better recognition
	Keyterms []string // Optional: provider-native vocabulary bias terms
	// ConversationContext carries the preceding dialogue turns (oldest
	// first, no speaker labels) for providers whose models condition on
	// conversational context — e.g. AssemblyAI Universal-3.5 Pro sync
	// accepts up to 100 turns / 4096 chars via conversation_context.
	// Distinct from Prompt (which describes the domain/scenario) and
	// Keyterms (explicit vocabulary). Providers without native support
	// ignore it.
	ConversationContext []string
	// ProviderProfileID prioritizes a provider for this request. Accepts a
	// full provider-profile ID (e.g. "stt.deepgram.nova-3") or a bare
	// provider ID (e.g. "deepgram"); routers move matching providers to the
	// front of their candidate list while keeping the remaining providers as
	// fallbacks. An unknown or unconfigured value changes nothing — a
	// request never hard-fails on an unsatisfiable preference. Mirrors
	// speechkit.DictationStreamOptions.ProviderProfileID for the batch path.
	ProviderProfileID         string
	Speaker                   speaker.Options                // Optional speaker diarization / attribution request
	Options                   provideropts.Values            // Optional normalized global/default voice options
	ProviderOptions           provideropts.Values            // Optional normalized overrides for the selected provider
	ProviderOptionsByProvider map[string]provideropts.Values // Optional provider-keyed overrides used by routers
}

type TranscriberOption func(*transcriberOptions)

type VPSProvider = OpenAICompatibleProvider

type WordConfidence struct {
	Text       string
	Confidence float64
	StartMs    int64
	EndMs      int64
}