text-to-speech AI Models

🤖 Model 📝 → 🔊

cjwbw/voicecraft

Performs zero-shot speech editing and text-to-speech synthesis using audio input and text transcripts. Supports four mai...

📝 → 🔊 • text-to-speech • voice-cloning • audio-to-audio • 11.2K runs

🤖 Model 📝 → 🔊

x-lance/f5-tts

Synthesize speech from text in a cloned voice using a reference audio sample. Provide a text prompt and speaker referenc...

📝 → 🔊 • text-to-speech • voice-cloning • 32.1K runs

🤖 Model 📝 → 🔊

resemble-ai/chatterbox-multilingual

Generate expressive multilingual speech from text. Accept a text prompt and a language selection (ar, da, de, el, en, es...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual-tts • 2.7K runs

🤖 Model 📝 → 🔊

platform-kit/mars5-tts

Generate English speech from text with zero-shot voice cloning from a 5–10s reference clip. Provide text, a short refere...

📝 → 🔊 • text-to-speech • voice-cloning • 517 runs

🤖 Model 📝 → 🔊

afiaka87/tortoise-tts

Generate speech from text with optional voice cloning from a reference voice sample. Accepts a text prompt and optional...

📝 → 🔊 • text-to-speech • voice-cloning • 172.5K runs

🤖 Model 📝 → 🔊

adirik/styletts2

Convert text to expressive speech, with optional speaker style cloning from a short reference audio. Accepts text input...

📝 → 🔊 • text-to-speech • voice-cloning • 131.8K runs

🤖 Model 📝 → 🔊

fermatresearch/spanish-f5-tts

Generate Spanish speech from text by cloning the voice from a reference audio. Provide Spanish text, a reference audio s...

📝 → 🔊 • text-to-speech • voice-cloning • spanish • 918 runs

🤖 Model 📝 → 🔊

awerks/neon-tts

Generate speech audio from text across 25 languages. Accepts text and a language selection; returns spoken audio. Suppor...

📝 → 🔊 • text-to-speech • multilingual • 161.0K runs

🤖 Model 📝 → 🔊

ttsds/voicecraft

Synthesizes speech from text using a reference audio file and its transcript to clone the speaker's voice. Takes text in...

📝 → 🔊 • voice-cloning • text-to-speech • 524 runs

🤖 Model 📝 → 🔊

microsoft/vibevoice

Generate long-form, multi-speaker conversational speech from a text script. Accepts a script and up to four selected voi...

📝 → 🔊 • text-to-speech • podcast-generation • multi-speaker-tts • 392 runs

🤖 Model 📝 → 🔊

usamaehsan/voices

Generate speech from text and convert voices. Use zero_shot voice cloning to synthesize speech in the style of a prompt_...

📝 → 🔊 • text-to-speech • voice-cloning • audio-to-audio • 877 runs

🤖 Model 📝 → 🔊

jichengdu/cosyvoice

Clone voices from audio samples with ultra-low latency streaming synthesis. Supports zero-shot voice cloning, cross-ling...

📝 → 🔊 • voice-cloning • text-to-speech • speech-translation • 1.9K runs

🤖 Model 📝 → 🔊

chenxwh/cosyvoice2-0.5b

Generate multilingual speech from text with zero-shot voice cloning. Provide a short reference audio clip and its transc...

📝 → 🔊 • text-to-speech • voice-cloning • 6.3K runs

🤖 Model 📝 → 🔊

ttsds/hierspeechpp_1_1

Converts text to speech using a speaker reference audio file to clone the voice characteristics and speaking style of th...

📝 → 🔊 • text-to-speech • voice-cloning • 258 runs

🤖 Model 📝 → 🔊

playht/play-dialog

Generate natural, conversational speech and two-speaker dialogues from text. Choose from preset voices (Angelo, Arsenio,...

📝 → 🔊 • text-to-speech • multi-voice-dialogue • emotion-tts • 26.8K runs

🤖 Model 📝 → 🔊

alphanumericuser/kokoro-82m

Converts text to speech using the Kokoro model with 82 million parameters, based on StyleTTS2 architecture. Supports mul...

📝 → 🔊 • text-to-speech • 7.7M runs

🤖 Model 📝 → 🔊

jichengdu/spark-tts

Generate spoken audio from text. Clone a target voice by providing a prompt audio sample (voice_cloning mode), or synthe...

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

🤖 Model 📝 → 🔊

ttsds/fishspeech_1_1

Generates speech from text input using a reference speaker audio and corresponding text. Takes text to synthesize, a ref...

📝 → 🔊 • text-to-speech • voice-cloning • 196 runs

🤖 Model 📝 → 🔊

codehappynice/voicegenerator

Clone a voice from a short reference audio and synthesize speech from text. Provide at least 6 seconds of speaker audio...

📝 → 🔊 • text-to-speech • voice-cloning • 39 runs

🤖 Model 📝 → 🔊

mosnfar/piper_persian

Convert Persian (Farsi) text to speech. Accepts a Persian text string and returns spoken audio. Runs fast on low-resourc...

📝 → 🔊 • text-to-speech • persian • farsi • 896 runs