Models tagged "text-to-speech"

🤖 Model 📝 → 🔊

e1100x/chattts

Generate conversational speech audio from text input. Specify a language (en or zh), choose a speaker or sample a random...

📝 → 🔊 • text-to-speech • multilingual-tts • 339 runs

🤖 Model 📝 → 🔊

ttsds/gptsovits_1

Clone a voice from a short reference audio and synthesize spoken audio from text. Accepts text, a language code (en, zh,...

📝 → 🔊 • text-to-speech • voice-cloning • 245 runs

🤖 Model 📝 → 🔊

ttsds/gptsovits_2

Generate speech from text in a cloned voice using a reference audio clip and its transcript. Accepts text plus a languag...

📝 → 🔊 • text-to-speech • voice-cloning • 412 runs

🤖 Model 📝 → 🔊

ttsds/hierspeechpp_1

Generate speech from text using a reference speaker’s voice. Takes a text prompt and a speaker_reference audio sample, a...

📝 → 🔊 • text-to-speech • voice-cloning • 144 runs

🤖 Model 📝 → 🔊

sruthiselvaraj/indicparlertts

Convert text to speech in Indic languages with natural-language voice control. Accepts a text prompt and a free-form voi...

📝 → 🔊 • text-to-speech • multilingual • voice-customization • 93 runs

🤖 Model 📝 → 🔊

cuuupid/mel-medarda-tts

Generate speech in the voice of Mel Medarda (Arcane) from text. Accepts a text prompt and outputs spoken audio; optional...

📝 → 🔊 • text-to-speech • voice-cloning • 6 runs

🤖 Model 📝 → 🔊

ttsds/hierspeechpp_lt460

Generate speech from text in the voice of a reference speaker. Accepts text and a speaker reference audio sample and out...

📝 → 🔊 • text-to-speech • voice-cloning • 227 runs

🤖 Model 📝 → 🔊

mayaresearch/veena-max

Generate expressive speech audio from English, Hindi, and Hindi–English code-mixed text. Provide text and choose a voice...

📝 → 🔊 • text-to-speech • hindi-tts • bilingual-tts • 40 runs

🤖 Model 📝 → 🔊

jbilcke/oute-tts

Generate speech audio from text with selectable multilingual voices. Accepts text and a speaker preset and returns spoke...

📝 → 🔊 • text-to-speech • multilingual-tts • 2.3K runs

🤖 Model 📝 → 🔊

ttsds/amphion_vevo

Generate speech from text with zero-shot voice cloning using a reference speaker audio. Provide a text prompt, select a...

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

🤖 Model 📝 → 🔊

datong-new/vc

Generate speech from text using the cloned voice of a speaker in a reference video. Provide a text script and a refer_vi...

📝 → 🔊 • text-to-speech • voice-cloning • 74 runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_5

Clone a target voice and synthesize speech from text input. Provide a speaker reference audio and its transcript (text_r...

📝 → 🔊 • text-to-speech • voice-cloning • 583 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_indic

Generate speech from text with reference-voice cloning for Indic languages. Accepts text, a speaker reference audio samp...

📝 → 🔊 • text-to-speech • voice-cloning • indic-languages • 214 runs

🤖 Model 📝 → 🔊

ttsds/amphion_valle

Generate speech from text with zero-shot voice cloning. Provide the text to synthesize, a speaker reference audio, and t...

📝 → 🔊 • text-to-speech • voice-cloning • 619 runs

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_2

Generate speech from text in a cloned voice using a reference audio sample. Provide the target text, a speaker reference...

📝 → 🔊 • text-to-speech • voice-cloning • 247 runs

🤖 Model 📝 → 🔊

prunaai/dia-1.6b

Generate multi-speaker dialogue audio from text. Use speaker labels like [S1], [S2] and parenthetical cues such as (laug...

📝 → 🔊 • text-to-speech • multi-speaker • 1.8K runs

🤖 Model 📝 → 🔊

thlz998/chat-tts

Generate conversational speech audio from text. Control prosody and paralinguistics with prompt tags like [laugh], [brea...

📝 → 🔊 • text-to-speech • multi-speaker • conversational-tts • 3.1K runs

🤖 Model 📝 → 🔊

nvidia/pdf-to-podcast

Generate podcast-style audio from a PDF document. Provide a PDF and optionally a topic guide, host and guest names, and...

📝 → 🔊 • podcast-generation • document-to-audio • text-to-speech • 620 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_mini_1_1_fixed

Generate speech from text input. Optionally mimic a target voice using a speaker_reference audio sample and guide prosod...

📝 → 🔊 • text-to-speech • voice-cloning • 193 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_mini_1_0

Generate speech audio from a text input, with optional voice cloning from a reference speaker audio. Guide delivery usin...

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