cinemasetfree.comafiaka87/tortoise-tts
Generate speech from text, clone voices from mp3 files. From James Betker AKA "neonbjb".
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
custom_voice | string(uri) | (Optional) Create a custom voice based on an mp3 file of a speaker. Audio should be at least 15 seconds, only contain one speaker, and be in mp3 format. Overrides the `voice_a` input. | — | — |
cvvp_amount | number | How much the CVVP model should influence the output. Increasing this can in some cases reduce the likelyhood of multiple speakers. Defaults to 0 (disabled) | 0 | min: 0, max: 1 |
preset | string | Which voice preset to use. See the documentation for more information. | "fast" | ultra_fastfaststandardhigh_quality |
seed | integer | Random seed which can be used to reproduce results. | 0 | — |
text | string | Text to speak. | "The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them." | — |
voice_a | string | Selects the voice to use for generation. Use `random` to select a random voice. Use `custom_voice` to use a custom voice. | "random" | angiecond_latent_exampledenirofreemanhalleljmyselfpat2snakestomtrain_dawstrain_dreamstrain_gracetrain_lescaultweaverapplejackdanielemmageraltjlawmolpatrainbowtim_reynoldstrain_atkinstrain_dotricetrain_empiretrain_kennardtrain_mousewilliamrandomcustom_voicedisabled |
voice_b | string | (Optional) Create new voice from averaging the latents for `voice_a`, `voice_b` and `voice_c`. Use `disabled` to disable voice mixing. | "disabled" | angiecond_latent_exampledenirofreemanhalleljmyselfpat2snakestomtrain_dawstrain_dreamstrain_gracetrain_lescaultweaverapplejackdanielemmageraltjlawmolpatrainbowtim_reynoldstrain_atkinstrain_dotricetrain_empiretrain_kennardtrain_mousewilliamrandomcustom_voicedisabled |
voice_c | string | (Optional) Create new voice from averaging the latents for `voice_a`, `voice_b` and `voice_c`. Use `disabled` to disable voice mixing. | "disabled" | angiecond_latent_exampledenirofreemanhalleljmyselfpat2snakestomtrain_dawstrain_dreamstrain_gracetrain_lescaultweaverapplejackdanielemmageraltjlawmolpatrainbowtim_reynoldstrain_atkinstrain_dotricetrain_empiretrain_kennardtrain_mousewilliamrandomcustom_voicedisabled |
custom_voicestring(Optional) Create a custom voice based on an mp3 file of a speaker. Audio should be at least 15 seconds, only contain one speaker, and be in mp3 format. Overrides the `voice_a` input.
cvvp_amountnumberHow much the CVVP model should influence the output. Increasing this can in some cases reduce the likelyhood of multiple speakers. Defaults to 0 (disabled)
0min: 0, max: 1presetstringWhich voice preset to use. See the documentation for more information.
"fast"seedintegerRandom seed which can be used to reproduce results.
0textstringText to speak.
"The expressiveness of autoregressive transformers is literally nuts! I absolutely adore them."voice_astringSelects the voice to use for generation. Use `random` to select a random voice. Use `custom_voice` to use a custom voice.
"random"voice_bstring(Optional) Create new voice from averaging the latents for `voice_a`, `voice_b` and `voice_c`. Use `disabled` to disable voice mixing.
"disabled"voice_cstring(Optional) Create new voice from averaging the latents for `voice_a`, `voice_b` and `voice_c`. Use `disabled` to disable voice mixing.
"disabled"e9658de4b325Updated: 7/25/2026173.3K runs