deepgram

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

type Provider 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
	// NoStore opts every request out of Deepgram's Model Improvement
	// Partnership Program, so audio and transcript are kept only for as long
	// as answering takes. Set by the host from its retention policy; the batch
	// path also honours the per-request option.
	NoStore       bool
	Keyterms      []string
	EndpointingMs int
	// contains filtered or unexported fields
}