Skip to content
Flow Like logo Flow Like Docs

Hugging Face TTS Options Node

AI/Generative/Audio/Options

Hugging Face TTS Options

Creates typed text-to-speech options for Hugging Face speech models.

ai_audio_tts_options_huggingfacemedia
Inputs3
Outputs1
Security exposure0/10
Packagemedia

Ratings

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

SecurityAttack surface and exposure impact.
0/10High
PrivacyPotential sensitivity of processed data.
0/10High
PerformanceRuntime or resource pressure.
1/10High
GovernancePolicy, audit, or compliance impact.
1/10High
ReliabilityOperational stability considerations.
0/10High
CostExternal or compute cost impact.
0/10High

Input Pins

3

Voice

String
voice

Optional voice parameter

Default auto

Format

String
output_format

Requested output audio format

Default mp3
mp3wavpcmopusaacflac+1 more

Speed

Float
speed

Playback speed multiplier. Use 0 for provider default.

Default 0
Range 0 to 4

Output Pins

1

Options

Struct
options

Typed text-to-speech provider options

TextToSpeechProviderOptionsTextToSpeechProviderOptions6 fields
variant 1objectvariant
providerconstrequired
const "default"
variant 2objectvariant
providerconstrequired
const "open_ai_compatible"
optionsOpenAiCompatibleTextToSpeechOptionsrequired
voicestring | null
default null
instructionsstring | null
default null
output_formatAudioOutputFormat
enum "mp3", "wav", "pcm", "opus"...default "mp3"
speednumber | null
format doubledefault null
variant 3objectvariant
providerconstrequired
const "xai"
optionsXaiTextToSpeechOptionsrequired
voicestring | null
default null
languagestring | null
default null
output_formatAudioOutputFormat
enum "mp3", "wav", "pcm", "opus"...default "mp3"
sample_rateinteger | null
format uint32default nullmin 0
bit_rateinteger | null
format uint32default nullmin 0
variant 4objectvariant
providerconstrequired
const "google"
optionsGoogleTextToSpeechOptionsrequired
voicestring | null
default null
instructionsstring | null
default null
languagestring | null
default null
output_formatAudioOutputFormat
enum "mp3", "wav", "pcm", "opus"...default "mp3"
variant 5objectvariant
providerconstrequired
const "hugging_face"
optionsHuggingFaceTextToSpeechOptionsrequired
voicestring | null
default null
output_formatAudioOutputFormat
enum "mp3", "wav", "pcm", "opus"...default "mp3"
speednumber | null
format doubledefault null
variant 6objectvariant
providerconstrequired
const "mistral"
optionsMistralTextToSpeechOptionsrequired
voicestring | null
default null
output_formatAudioOutputFormat
enum "mp3", "wav", "pcm", "opus"...default "mp3"
Schema enforced

Node Info

Internal name
ai_audio_tts_options_huggingface
Category
AI/Generative/Audio/Options
Version
1