Models tagged "text-to-speech"

🤖 Model 📝 → 🔊

ttsds/parlertts_mini_expresso

Generate speech audio from text, with optional voice cloning using a speaker reference clip. Guide voice style and proso...

📝 → 🔊 • text-to-speech • voice-cloning • 195 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_large_1_0

Generate speech audio from text with optional zero-shot voice cloning via a short speaker reference clip. Control prosod...

📝 → 🔊 • text-to-speech • voice-cloning • 256 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_mini_0_1

Convert text to speech with optional voice cloning from a reference audio sample. Accept a required text input and optio...

📝 → 🔊 • text-to-speech • voice-cloning • 198 runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_2_sft

Generate speech from text using a reference speaker audio clip and its transcript for voice cloning. Provide the text to...

📝 → 🔊 • text-to-speech • voice-cloning • 253 runs

🤖 Model 📝 → 🔊

ttsds/bark

Generate speech audio from text using a reference voice sample. Accepts a text prompt, a speaker reference audio, and a...

📝 → 🔊 • text-to-speech • voice-cloning • 499 runs

🤖 Model 📝 → 🔊

holywalley/bel-tts

Generate Belarusian speech from text. Accept Belarusian text or phonemized input (per bel-tts guidelines) to control pro...

📝 → 🔊 • text-to-speech • belarusian • 1.4K runs

🤖 Model 📝 → 🔊

lilcats/kitten-tts

Generate speech from text input using an ultra-lightweight, CPU-friendly text-to-speech model. Supports multiple built-i...

📝 → 🔊 • text-to-speech • tts • cpu-friendly • 7 runs

🤖 Model 📝 → 🔊

dessix/moss-ttsd

Generate two-speaker conversational speech from a text dialogue script. Accept a script with [S1]/[S2] turns and optiona...

📝 → 🔊 • text-to-speech • voice-cloning • dialogue-tts • 694 runs

🤖 Model 📝 → 🔊

ttsds/speecht5

Convert text to spoken audio, optionally cloning a target voice from a short speaker reference clip. Accepts text and an...

📝 → 🔊 • text-to-speech • voice-cloning • 190 runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_0

Generate speech audio from text with voice cloning. Provide the text to speak, a speaker reference audio clip, and the t...

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

🤖 Model 📝 → 🔊

andreasjansson/parler-tts

Generate speech audio from text with natural-language voice control. Accept a text prompt and a descriptive voice prompt...

📝 → 🔊 • text-to-speech • 995 runs

🤖 Model 📝 → 🔊

camb-ai/mars5-tts

Clone a voice and synthesize English speech from text using a short reference audio sample. Accepts a text prompt, a bri...

📝 → 🔊 • text-to-speech • voice-cloning • 679 runs

🤖 Model 📝 → 🔊

jichengdu/fish-speech

Generate speech from text in a cloned voice using zero-shot or few-shot reference audio. Provide target text, a 10–30s s...

📝 → 🔊 • text-to-speech • voice-cloning • 639 runs

🤖 Model 📝 → 🔊

lucataco/seamless_communication

Translate speech and text across 100+ languages, returning text and optionally translated speech audio. Supports speech-...

📝 → 🔊 • speech-translation • speech-to-text • text-to-speech • 909 runs

🤖 Model 📝 → 🔊

cjwbw/melotts

Generate speech from text across multiple languages. Accepts text input with language selection (EN, ES, FR, ZH, JP, KR)...

📝 → 🔊 • text-to-speech • multilingual • 1.4K runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_1_large

Clone a voice and generate speech from text using a reference audio clip and its transcript. Provide target text to spea...

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

🤖 Model 📝 → 🔊

ttsds/amphion_naturalspeech2

Generate speech from text using a reference speaker clip for zero-shot voice cloning. Provide a text prompt and an audio...

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

🤖 Model 📝 → 🔊

lucataco/step-audio-tts-3b

Generate speech, rap, and humming from text. Input a text prompt and select a preset voice (闫雨婷, 闫雨婷RAP, 闫雨婷VOCAL); outp...

📝 → 🔊 • text-to-speech • singing-voice-generation • rap • 1.1K runs

🤖 Model 📝 → 🔊

nyxynyx/f5-tts

Generate cloned-voice speech from text using a reference audio sample. Accepts text (gen_text) and reference audio (ref_...

📝 → 🔊 • text-to-speech • voice-cloning • 22.4K runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_4

Generate speech from text using a reference voice. Provide the text to speak, a short speaker reference audio clip, and...

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