Skip to content
Flow Like logo Flow Like Docs

Local Text to Speech Node

AI/Generative/Audio

Local Text to Speech

Generates WAV speech locally with an installed any-tts model bit.

ai_audio_local_text_to_speechmediaLong running
Inputs11
Outputs3
Security exposure5/10
Packagemedia

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.
5/10Medium
PrivacyPotential sensitivity of processed data.
6/10Medium
PerformanceRuntime or resource pressure.
5/10Medium
GovernancePolicy, audit, or compliance impact.
4/10Medium
ReliabilityOperational stability considerations.
4/10Medium
CostExternal or compute cost impact.
7/10Low

Input Pins

11

Input

Execution
exec_in

Trigger local speech generation

TTS Model

Struct
bit

Installed TTS model Bit

BitBit19 fields
idstring
default ""
typeBitTypes
enum "Llm", "Vlm", "Tts", "Stt"...default "Other"
metaMap<string, Metadata>
default {}
*Metadatamap value
namestringrequired
descriptionstringrequired
long_descriptionstring | null
release_notesstring | null
tagsArray<string>required
itemsstringarray item
+11 more fields
authorsArray<string>
default []
itemsstringarray item
repositorystring | null
default null
download_linkstring | null
default null
file_namestring | null
default null
hashstring
default ""
sizeinteger | null
format uint64default nullmin 0
hubstring
default ""
parametersvalue
default null
versionstring | null
default null
licensestring | null
default null
dependenciesArray<string>
default []
itemsstringarray item
dependency_tree_hashstring
default ""
createdstring
default ""
updatedstring
default ""
model_slugstring | null
default null
+1 more fields
Schema enforced

Text

String
text

Text to synthesize

Output Path

Struct
output_path

Destination FlowPath for generated WAV audio

FlowPathFlowPath3 fields
pathstringrequired
store_refstringrequired
cache_store_refstring | null
Schema enforced

Language

String
language

Optional language code or name. Use auto for model default.

Default auto

Voice

String
voice

Optional voice or speaker name. Use auto for model default.

Default auto

Instruction

String
instruct

Optional style instruction for models that support it

Max Tokens

Integer
max_tokens

Optional generation token limit. Use 0 for model default.

Default 0

Temperature

Float
temperature

Optional sampling temperature. Use 0 for model default.

Default 0

CFG Scale

Float
cfg_scale

Optional guidance scale. Use 0 for model default.

Default 0

Reference Audio

Struct
reference_audio

Optional FlowPath to WAV or MP3 reference audio for voice cloning

FlowPathFlowPath3 fields
pathstringrequired
store_refstringrequired
cache_store_refstring | null

Output Pins

3

Output

Execution
exec_out

Done

Path

Struct
path

Generated WAV path

FlowPathFlowPath3 fields
pathstringrequired
store_refstringrequired
cache_store_refstring | null

Metadata

Struct
metadata

Local synthesis metadata

Node Info

Internal name
ai_audio_local_text_to_speech
Category
AI/Generative/Audio
Version
4