Class UTryllSpeakParams¶

#include <TryllSpeakParams.h>

Inherits the following classes: UTryllNodeParamsBase

Public Attributes¶

Type	Name
FString	DefaultExit
FTryllSlotInput	Input
int32	MinSentenceChars = `12`
int32	SpeakerId = `0`
float	Speed = `1.0f`
FString	TtsDeliveryInstruction
FString	TtsLang
FTryllModelName	TtsModelName
FTryllStoragePath	TtsVoice
FString	TtsVoiceDescription
bool	bOverrideInput = `false`
bool	bOverrideTtsDeliveryInstruction = `false`
bool	bOverrideTtsLang = `false`
bool	bOverrideTtsModelName = `false`
bool	bOverrideTtsVoiceDescription = `false`

Public Functions¶

Type	Name
virtual ETryllNodeType	GetNodeType () override const
virtual flatbuffers::Offset< void >	Pack (flatbuffers::FlatBufferBuilder & Fbb, Tryll::NodeParams::NodeParams & OutType) override const

Public Functions inherited from UTryllNodeParamsBase¶

See UTryllNodeParamsBase

Type	Name
virtual TArray< FString >	GetExitTargetOptions () const
virtual ETryllNodeType	GetNodeType () const
FString	GetOwnerNodeName () const
virtual flatbuffers::Offset< void >	Pack (flatbuffers::FlatBufferBuilder & Fbb, ::Tryll::NodeParams::NodeParams & OutType) const
ETryllNodeType return	static_cast (0)

Public Static Functions inherited from UTryllNodeParamsBase¶

See UTryllNodeParamsBase

Type	Name
const FTryllGraphDescription *	FindEnclosingGraph (const UObject * Obj)

Detailed Description¶

Standalone TTS-only node. Voices its input-resolved slot (any upstream node's output — Generate, CannedResponse, etc. — or user_message itself), segments it into sentences, and synthesizes each on a dedicated TTS strand, emitting PCM frames via OnTtsAudio callbacks. Unlike GenerateAndSpeak it runs no LLM inference, so it can voice canned/scripted lines or any upstream-produced answer without paying for a generation pass.

Public Attributes Documentation¶

variable DefaultExit¶

FString UTryllSpeakParams::DefaultExit;

Default exit target — routes here after synthesis completes. Empty string = END. Graph exit "default" — target node name; empty = END.

variable Input¶

FTryllSlotInput UTryllSpeakParams::Input;

Upstream inter-node slot this field consumes. Empty = context default.

variable MinSentenceChars¶

int32 UTryllSpeakParams::MinSentenceChars;

Minimum characters before a sentence boundary fires. Lower values reduce first-utterance latency at the cost of more, smaller TTS calls.

variable SpeakerId¶

int32 UTryllSpeakParams::SpeakerId;

TTS speaker / voice index (default 0). Valid range is 0 to the model's speaker count minus 1 — the shipped Supertonic 3 bundle has 10 voice styles (0–9); Pocket TTS is single-speaker, so it must stay 0 there (pick a Pocket voice with tts_voice instead). Agent creation fails with an out-of-range error for values the model cannot satisfy.

variable Speed¶

float UTryllSpeakParams::Speed;

TTS speech-rate multiplier. 1.0 = native speed.

variable TtsDeliveryInstruction¶

FString UTryllSpeakParams::TtsDeliveryInstruction;

variable TtsLang¶

FString UTryllSpeakParams::TtsLang;

variable TtsModelName¶

FTryllModelName UTryllSpeakParams::TtsModelName;

variable TtsVoice¶

FTryllStoragePath UTryllSpeakParams::TtsVoice;

Reference-voice WAV for zero-shot voice-cloning families (Pocket TTS): a path relative to the session storage root pointing at a 10–20 s clean mono recording of the target voice. Empty = the model's default voice. Ignored by fixed-voice families (use speaker_id there).

variable TtsVoiceDescription¶

FString UTryllSpeakParams::TtsVoiceDescription;

variable bOverrideInput¶

bool UTryllSpeakParams::bOverrideInput;

Slot name this node voices. Empty = "user_message" (same default as every other input-bearing node). Structural: immutable after creation — rebinding would re-wire the slot dataflow that is validated once at agent creation. Set to true to override the inherited Input value.

variable bOverrideTtsDeliveryInstruction¶

bool UTryllSpeakParams::bOverrideTtsDeliveryInstruction;

Natural-language sustained delivery direction for this synthesis call. Empty = neutral / model default. Set to true to override the inherited TtsDeliveryInstruction value.

variable bOverrideTtsLang¶

bool UTryllSpeakParams::bOverrideTtsLang;

TTS language hint for multilingual models that select the language per call (e.g. Supertonic 3: "en", "de", "fr", …). Resolution order: this param, then the session locale (CreateSessionRequest.locale), then the model's catalog default. Set it only to override the session — one character who keeps speaking French in a German playthrough. For a whole-game language switch, set the session locale instead and leave this empty: it reaches every agent and every node with no per-node mutation. Ignored by families whose language is fixed by the model itself (e.g. Pocket TTS per-language models). Set to true to override the inherited TtsLang value.

variable bOverrideTtsModelName¶

bool UTryllSpeakParams::bOverrideTtsModelName;

TTS model catalog name. Optional — when empty the server uses the first available TTS voice in the model catalog. Set it to pick a specific voice. Set to true to override the inherited TtsModelName value.

variable bOverrideTtsVoiceDescription¶

bool UTryllSpeakParams::bOverrideTtsVoiceDescription;

Natural-language stable voice identity: age, accent, pitch, timbre and baseline pacing. Empty = use speaker_id / catalog default. Appended after default_exit so existing FlatBuffers field IDs do not move. Set to true to override the inherited TtsVoiceDescription value.

Public Functions Documentation¶

function GetNodeType¶

inline virtual ETryllNodeType UTryllSpeakParams::GetNodeType () override const

Implements UTryllNodeParamsBase::GetNodeType

function Pack¶

virtual flatbuffers::Offset< void > UTryllSpeakParams::Pack (
    flatbuffers::FlatBufferBuilder & Fbb,
    Tryll::NodeParams::NodeParams & OutType
) override const

Implements UTryllNodeParamsBase::Pack

The documentation for this class was generated from the following file C:/_tryll/_monorepo3/tryll/clients/unreal/Source/TryllClient/Public/Generated/Nodes/TryllSpeakParams.h