Docs /Templates/ sinapsis-zonos

ZonosTTS

sinapsis-zonosZonosaudioaudio_generationzonosspeech

Python template · sinapsis_zonos.templates.zonos_tts

Overview

Base template for speech synthesis using the Zonos model.

This template is designed to generate high-quality, expressive text-to-speech (TTS) outputs using the Zonos TTS model, which supports multilingual speech generation, speaker cloning, and fine control over various speech attributes like pitch, speaking rate, and emotions.

Capabilities

Capabilities: not set

Installation

Install the published package using pip or uv.

Terminalbash
pip install sinapsis-zonos==1.0.0
uv pip install sinapsis-zonos==1.0.0
uv add sinapsis-zonos==1.0.0

Configuration

Effective fields from the inspector schema, including nested Pydantic model fields.

fmax

Max frequency for speech in Hz (default: 22050, range: 0-24000).

float
Optional
Default: 22050
seed
int
Optional
Default: 420
model

Model identifier for Zonos. Options: "Zyphra/Zonos-v0.1-transformer", "Zyphra/Zonos-v0.1-hybrid" (default: "Zyphra/Zonos-v0.1-transformer").

typing.Literal['Zyphra/Zonos-v0.1-transformer', 'Zyphra/Zonos-v0.1-hybrid']
Optional
Default: "Zyphra/Zonos-v0.1-transformer"
dnsmos

Denoising strength for hybrid models (default: 4.0, range: 1-5).

float
Optional
Default: 4
emotions

Emotions to apply to generated speech, fine-tuning emotional tone.

EmotionsConfig
Optional
Default: null
fear
float
Optional
Default: 0
anger
float
Optional
Default: 0
other
float
Optional
Default: 0
disgust
float
Optional
Default: 0
neutral
float
Optional
Default: 0
sadness
float
Optional
Default: 0
surprise
float
Optional
Default: 0
happiness
float
Optional
Default: 0
language

Language for speech synthesis (default: 'en-us').

str
Optional
Default: "en-us"
metadata
sinapsis_core.template_base.base_models.TemplateMetadata | None
Optional
Default: null
vq_score

VQ score for hybrid models (default: 0.78, range: 0.5-0.8).

float
Optional
Default: 0.7
cfg_scale

Controls randomness in speech (default: 2.0, range: 1-5).

float
Optional
Default: 2
pitch_std

Standard deviation for pitch variation (default: 20.0, range: 0-300).

float
Optional
Default: 20
prefix_audio

Path to an audio file for prefix conditioning (e.g., whispering).

str | None
Optional
Default: null
speaker_audio

Path to an audio file for creating a speaker embedding for voice cloning. output_folder (str): Folder for saving generated audio files (default: SINAPSIS_CACHE_DIR/zonos/audios).

str | None
Optional
Default: null
speaking_rate

Rate of speech (default: 15.0, range: 5-30).

float
Optional
Default: 15
randomized_seed

If True, the seed is randomized (default: True).

bool
Optional
Default: true
sampling_params

Controls sampling behavior, including `top_p`, `top_k`, `min_p`, `linear`, `conf`, and `quad` parameters for sampling.

SamplingParams
Optional
Default: null
conf

Confidence level for randomness. Range: -2.0 to 2.0. Default: 0.0.

float
Optional
Default: 0
quad

Controls how much low probabilities are reduced. Range: -2.0 to 2.0. Default: 0.0.

float
Optional
Default: 0
min_p

Minimum token probability, scaled by the highest token probability. Range: 0-1. Default: 0.0.

float
Optional
Default: 0
top_k

Number of top tokens to sample from. Range: 0-1024. Default: 0.

int
Optional
Default: 0
top_p

Cumulative probability threshold for nucleus sampling. Range: 0-1. Default: 0.0.

float
Optional
Default: 0
linear

Controls the token unusualness. Range: -2.0 to 2.0. Default: 0.0.

float
Optional
Default: 0
denoised_speaker

If True, applies denoising to speaker embedding.

bool
Optional
Default: false
unconditional_keys

Keys for conditioning speech without speaker embedding.

typing.Set[str]
Optional
Default: null

Configuration example

Generated from documented defaults. Replace any placeholders and complete required nested settings before running.

yaml
templates:
  - template_name: "ZonosTTS"
    class_name: "ZonosTTS"
    attributes:
      fmax: 22050
      seed: 420
      model: "Zyphra/Zonos-v0.1-transformer"
      dnsmos: 4
      emotions:
        fear: 0
        anger: 0
        other: 0
        disgust: 0
        neutral: 0
        sadness: 0
        surprise: 0
        happiness: 0
      language: "en-us"
      vq_score: 0.7
      cfg_scale: 2
      pitch_std: 20
      prefix_audio: null
      speaker_audio: null
      speaking_rate: 15
      randomized_seed: true
      sampling_params:
        conf: 0
        quad: 0
        min_p: 0
        top_k: 0
        top_p: 0
        linear: 0
      denoised_speaker: false
      unconditional_keys: null

Inheritance

Immediate parent: sinapsis_core.template_base.template.Template

Environment variables

Environment definitions belong to their canonical Python modules.

No directly related environment variables listed.