> ## Documentation Index
> Fetch the complete documentation index at: https://omnicron.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Text To Speech

> Text to speech using the **zsxkib/realistic-voice-cloning** AI Model.

### Query

<ParamField query="model" type="string" default="zsxkib/realistic-voice-cloning" required>
  The voice model to be used;
</ParamField>

### Body

<ParamField body="song_input" type="file" required>
  Upload your audio file here.
</ParamField>

<ParamField body="rvc_model" type="string" default="Squidward">
  RVC model for a specific voice. If using a custom model, this should match the name of the downloaded model. If a 'custom\_rvc\_model\_download\_url' is provided, this will be automatically set to the name of the downloaded model.
</ParamField>

<ParamField body="custom_rvc_model_download_url" type="string">
  URL to download a custom RVC model. If provided, the model will be downloaded (if it doesn't already exist) and used for prediction, regardless of the 'rvc\_model' value.
</ParamField>

<ParamField body="pitch_change" type="string" default="no-change">
  Adjust pitch of AI vocals. Options: `no-change`, `male-to-female`, `female-to-male`.
</ParamField>

<ParamField body="index_rate" type="float" default="0.5">
  Control how much of the AI's accent to leave in the vocals.
</ParamField>

<ParamField body="filter_raidus" type="int" default="3">
  If >=3: apply median filtering median filtering to the harvested pitch results.
</ParamField>

<ParamField body="rms_mix_rate" type="float" default="0.25">
  Control how much to use the original vocal's loudness (0) or a fixed loudness (1).
</ParamField>

<ParamField body="pitch_detection_algorithm" type="string" default="rmvpe">
  Best option is rmvpe (clarity in vocals), then mangio-crepe (smoother vocals).
</ParamField>

<ParamField body="crepe_hop_length" type="int" default="128">
  When `pitch_detection_algo` is set to `mangio-crepe`, this controls how often it checks for pitch changes in milliseconds. Lower values lead to longer conversions and higher risk of voice cracks, but better pitch accuracy.
</ParamField>

<ParamField body="protect" type="float" default="0.33">
  Control how much of the original vocals' breath and voiceless consonants to leave in the AI vocals. Set 0.5 to disable.
</ParamField>

<ParamField body="main_vocals_volume_change" type="float" default="10.0">
  Control volume of main AI vocals. Use -3 to decrease the volume by 3 decibels, or 3 to increase the volume by 3 decibels.
</ParamField>

<ParamField body="backup_vocals_volume_change" type="float" default="0.0">
  Control volume of backup AI vocals.
</ParamField>

<ParamField body="instrumental_volume_change" type="float" default="0.0">
  Control volume of the background music/instrumentals.
</ParamField>

<ParamField body="pitch_change_all" type="float" default="0.0">
  Change pitch/key of background music, backup vocals and AI vocals in semitones. Reduces sound quality slightly.
</ParamField>

<ParamField body="reverb_size" type="float" default="0.15">
  The larger the room, the longer the reverb time.
</ParamField>

<ParamField body="reverb_wetness" type="float" default="0.2">
  Level of AI vocals with reverb.
</ParamField>

<ParamField body="reverb_dryness" type="float" default="0.8">
  Level of AI vocals with reverb.
</ParamField>

<ParamField body="reverb_damping" type="float" default="0.7">
  Absorption of high frequencies in the reverb.
</ParamField>

<ParamField body="output_format" type="string" default="mp3">
  wav for best quality and large file size, mp3 for decent quality and small file size.
</ParamField>