text-to-speech AI Models

🤖 Model 📝 → 🔊

e1100x/chattts

Generate conversational speech from text input for LLM assistants, chatbots, and dialogue. Supports multilingual synthes...

📝 → 🔊 • text-to-speech • multilingual-tts • 358 runs

🤖 Model 📝 → 🔊

ttsds/gptsovits_1

Converts text to speech using voice cloning technology with support for English, Chinese, and Japanese languages. Takes...

📝 → 🔊 • text-to-speech • voice-cloning • 248 runs

🤖 Model 📝 → 🔊

ttsds/gptsovits_2

Generates speech audio from text input using voice cloning with a speaker reference audio file and corresponding text re...

📝 → 🔊 • text-to-speech • voice-cloning • 427 runs

🤖 Model 📝 → 🔊

ttsds/hierspeechpp_1

Generate speech from text using a reference speaker audio. Mimic the timbre and speaking style of the provided voice sam...

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

🤖 Model 📝 → 🔊

sruthiselvaraj/indicparlertts

Generate speech from text with natural-language voice descriptions. Accepts a text prompt and a voice description to con...

📝 → 🔊 • text-to-speech • multilingual • voice-style-control • 94 runs

🤖 Model 📝 → 🔊

cuuupid/mel-medarda-tts

Convert text to spoken audio in the voice of Mel Medarda from Arcane. Accepts text and optionally a short reference audi...

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

🤖 Model 📝 → 🔊

ttsds/hierspeechpp_lt460

Converts text into speech using a reference speaker audio to clone the voice. Takes text input and a speaker reference a...

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

🤖 Model 📝 → 🔊

mayaresearch/veena-max

Generate expressive Hindi, English, and Hindi–English code-mixed speech from text with selectable voices. Accepts text p...

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

🤖 Model 📝 → 🔊

jbilcke/oute-tts

Convert text to speech audio with selectable multilingual voices. Accepts text and a speaker choice; returns synthesized...

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

🤖 Model 📝 → 🔊

ttsds/amphion_vevo

Generate speech from text with zero-shot voice cloning using a reference voice sample. Accepts text, a speaker reference...

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

🤖 Model 📝 → 🔊

datong-new/vc

Generate speech from text using the voice of a speaker extracted from a reference video or audio clip. Provide text and...

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

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_5

Generate speech in a cloned voice from text input. Provide target text, a speaker reference audio, and the transcript of...

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

🤖 Model 📝 → 🔊

ttsds/parlertts_indic

Generate speech audio from a text input. Optionally clone a target voice by supplying a short speaker reference audio, a...

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

🤖 Model 📝 → 🔊

ttsds/amphion_valle

Generate speech from text with zero-shot voice cloning using a speaker reference audio and its transcript. Provide a tex...

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

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_2

Generates speech audio from text input using a reference audio sample and corresponding reference text to clone the spea...

📝 → 🔊 • text-to-speech • voice-cloning • 248 runs

🤖 Model 📝 → 🔊

prunaai/dia-1.6b

Generate spoken dialogue audio from a text script. Parse speaker tags like [S1], [S2] and parenthetical stage directions...

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

🤖 Model 📝 → 🔊

thlz998/chat-tts

Generate conversational speech from text with controllable prosody and paralinguistic cues. Add laughs, pauses, and oral...

📝 → 🔊 • text-to-speech • voice-generation • 3.1K runs

🤖 Model 📝 → 🔊

nvidia/pdf-to-podcast

Convert a PDF into a podcast-style audio episode. Provide a PDF and optionally guide the topic, choose a dialogue betwee...

📝 → 🔊 • text-to-speech • pdf-to-audio • podcast-generation • 650 runs

🤖 Model 📝 → 🔊

ttsds/parlertts_mini_1_1_fixed

Generate spoken audio from text, optionally cloning a target voice from a short speaker reference audio. Accepts text as...

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

🤖 Model 📝 → 🔊

ttsds/parlertts_mini_1_0

Converts text input into spoken audio output using the Parler-TTS Mini 1.0 model. Accepts optional speaker reference aud...

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