voice-cloning AI Models

🤖 Model 📝 → 🔊

dessix/moss-ttsd

Converts dialogue scripts between two speakers into natural, expressive conversational speech. Supports bilingual synthe...

📝 → 🔊 • text-to-speech • voice-cloning • 895 runs

🤖 Model 📝 → 🔊

ttsds/speecht5

Convert text to speech with optional voice cloning from a reference audio sample. Accepts text and an optional speaker r...

📝 → 🔊 • text-to-speech • voice-cloning • 192 runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_0

Generate speech from text input using a speaker reference audio and corresponding text reference. Takes text to be spoke...

📝 → 🔊 • text-to-speech • voice-cloning • 184 runs

🤖 Model 📝 → 🔊

camb-ai/mars5-tts

Converts text to speech with voice cloning capabilities using a reference audio file. Takes a text prompt and a referenc...

📝 → 🔊 • text-to-speech • voice-cloning • 716 runs

🤖 Model 📝 → 🔊

jichengdu/fish-speech

Clone voices and synthesize speech from text using a short reference audio clip (10–30 seconds) and its transcript. Acce...

📝 → 🔊 • text-to-speech • voice-cloning • 649 runs

🤖 Model 🔊

cuuupid/seamless_expressive

Translate speech between English, French, Spanish, German, Italian, and Chinese while preserving the speaker’s style, pr...

🔊 • speech-translation • audio-to-audio • 807 runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_1_large

Generate speech from text with voice cloning conditioned on a speaker reference recording and its transcript. Mimic the...

📝 → 🔊 • text-to-speech • voice-cloning • 236 runs

🤖 Model 📝 → 🔊

ttsds/amphion_naturalspeech2

Convert text to speech in a target speaker’s voice using a short reference audio clip. Provide text and a speaker refere...

📝 → 🔊 • text-to-speech • voice-cloning • 244 runs

🤖 Model

zsxkib/create-rvc-dataset

Create an RVC v2 voice cloning dataset from a YouTube video. Provide a YouTube URL and optionally a dataset name; it dow...

music-source-separation • voice-cloning • dataset-preparation • 15.2K runs

🤖 Model 🔊

lucataco/singing_voice_conversion

Convert a singing voice in an input audio to sound like a selected target singer. Transform source vocals to the timbre...

🔊 • audio-to-audio • voice-cloning • singing-voice-conversion • 1.0K runs

🤖 Model 📝 → 🔊

nyxynyx/f5-tts

Clone a speaker’s voice from a reference audio and synthesize speech from text. Accepts a text prompt and a reference au...

📝 → 🔊 • text-to-speech • voice-cloning • 22.7K runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_4

Generate speech audio from text while cloning a target voice from a reference audio sample. Provide the text to speak, a...

📝 → 🔊 • text-to-speech • voice-cloning • 219 runs

🤖 Model 📝 → 🔊

ttsds/styletts2

Converts text input into spoken audio output using StyleTTS2 technology. Accepts an optional speaker reference audio fil...

📝 → 🔊 • text-to-speech • voice-cloning • 335 runs

🤖 Model 📝 → 🔊

ttsds/whisperspeech

Generate speech from text in the voice of a reference speaker. Provide text and a speaker reference audio sample; receiv...

📝 → 🔊 • text-to-speech • voice-cloning • 1.3K runs

🤖 Model 📝 → 🔊

ttsds/amphion_maskgct

Synthesize speech from text using a short reference voice clip (zero-shot TTS). Clone a target speaker’s voice in Englis...

📝 → 🔊 • text-to-speech • voice-cloning • 483 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_tiny_1_0

Converts text into spoken audio using the Parler TTS tiny 1.0 model. Takes text input and optional speaker reference aud...

📝 → 🔊 • text-to-speech • voice-cloning • 200 runs

🤖 Model 📝 → 🔊

bzikst/xtts-v2-fork

Clone a voice and synthesize speech from text in 17 languages. Provide a short reference speaker clip (at least 6 second...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual • 451 runs

🤖 Model 📝 → 🔊

ttsds/bark_small

Generate speech from text using a reference voice sample. Provide text, a language code (en, de, es, it, ja, pl, pt, tr)...

📝 → 🔊 • text-to-speech • voice-cloning • 229 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_mini_multilingual

Generate speech audio from text with optional voice cloning from a reference audio clip. Accept a speaker reference audi...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual • 200 runs

🤖 Model 📝 → 🔊

jaaari/zonos

Generate expressive speech from text with optional voice cloning from a short reference clip. Accept a text prompt and a...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual-tts • 4.9K runs