Models tagged "text-to-speech"

🤖 Model 📝 → 🔊

ttsds/styletts2

Generate speech from text with optional voice cloning from a reference audio sample. Accepts text plus an optional speak...

📝 → 🔊 • text-to-speech • voice-cloning • speech-style-transfer • 334 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

Generate speech audio from text, with optional voice cloning conditioned on a reference recording. Accepts text, an opti...

📝 → 🔊 • text-to-speech • voice-cloning • speech-style-transfer • 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

🤖 Model 📝 → 🔊

cuuupid/zonos

Generate speech from text with optional voice cloning from a short reference audio. Accept text plus a 5–30s speaker sam...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual • 267 runs

🤖 Model 📝 → 🔊

lucataco/whisperspeech-small

Convert text to speech with optional zero-shot voice cloning. Accept a text prompt and an optional speaker reference aud...

📝 → 🔊 • text-to-speech • voice-cloning • 1.6K runs

🤖 Model 📝 → 🔊

codingayam/kokoro-82m-complete

Generate speech audio from text input. Select from multiple built-in voices (e.g., af_heart, af_bella, af_alloy, af_aoed...

📝 → 🔊 • text-to-speech • 102 runs

🤖 Model 📝 → 🔊

zsxkib/hololive-style-bert-vits2

Generate Hololive VTuber-style speech from text or convert a reference audio clip into those voices. Takes text input or...

📝 → 🔊 • text-to-speech • audio-to-audio • speech-style-transfer • 886 runs

🤖 Model 📝 → 🔊

kimanh2023/xvdsdfstevbrsgwesfgesaraw

Generate speech in a cloned voice from text input. Provide a reference audio clip and its transcript to capture the targ...

📝 → 🔊 • voice-cloning • text-to-speech • 24 runs

🤖 Model 📝 → 🔊

suminhthanh/vixtts

Clone a speaker’s voice from a 6-second sample and synthesize speech from text in Vietnamese and 17 other languages. Acc...

📝 → 🔊 • text-to-speech • voice-cloning • 512 runs

🤖 Model 📝 → 🔊

datong-new/tts-zh

Generate Chinese and English speech audio from text. Accepts text and a voice_type and outputs narrated audio. Select vo...

📝 → 🔊 • text-to-speech • chinese • cantonese • 198 runs

🤖 Model

kwaivgi/kling-lip-sync

Lip-sync faces in a short video to match input speech from an audio file or synthesized speech from text. Provide a 2–10...

lipsync • 18.8K runs

🤖 Model 📝 → 🔊

kjjk10/llasa-3b-long

Clone a voice from a short reference sample and synthesize speech from text. Provide a voice sample and target text to g...

📝 → 🔊 • text-to-speech • voice-cloning • 1.5K runs

🤖 Model 📝 → 🔊

adirik/hierspeechpp

Generate speech in a target voice from text or reference speech. Accepts a text prompt or an input audio clip for conten...

📝 → 🔊 • text-to-speech • voice-cloning • audio-to-audio • 4.6K runs

🤖 Model 📝 → 🔊

tuannha/f5-tts-vi

Generate Vietnamese speech from text with zero-shot voice cloning from a reference audio sample. Accepts input text, a r...

📝 → 🔊 • text-to-speech • voice-cloning • vietnamese • 84 runs

🤖 Model

minimax/voice-cloning

Clone a speaker’s voice from an audio recording for use with MiniMax text-to-speech models. Input an MP3/M4A/WAV clip (1...

voice-cloning • 19.2K runs