text-to-speech AI Models

🤖 Model 📝 → 🔊

minimax/speech-02-hd

Generate speech audio from text with multilingual voices, emotion control, and voice cloning. Accepts text (up to 10,000...

📝 → 🔊 • text-to-speech • voice-cloning • 971.1K runs

🤖 Model 📝 → 🔊

cjwbw/seamless_communication

Translate speech and text across 100+ languages, returning text and optionally synthesized speech. Accept audio or text...

📝 → 🔊 • speech-translation • speech-to-text • text-to-speech • 89.0K runs

🤖 Model 📝 → 🔊

zsxkib/kimi-audio-7b-instruct

Processes audio input to perform multiple audio tasks including speech-to-text transcription, audio captioning, emotion...

📝 → 🔊 • speech-to-text • text-to-speech • audio-to-audio • 3.7K runs

🤖 Model 📝 → 🔊

resemble-ai/chatterbox

Generate expressive, natural speech from text prompts with unique emotion control and instant voice cloning capabilities...

📝 → 🔊 • text-to-speech • voice-cloning • audio-embedding • 408.7K runs

🤖 Model 📝 → 🔊

ttsds/metavoice

Generate speech from text using a reference speaker audio to clone the speaker’s voice. Accepts a text prompt and a spea...

📝 → 🔊 • text-to-speech • voice-cloning • 646 runs

🤖 Model 📝 → 🔊

ttsds/tortoise

Converts text into spoken audio using a speaker reference audio file to clone the voice characteristics and speaking sty...

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

🤖 Model 📝 → 🔊

ttsds/openvoice_2

Generate speech from text with a cloned voice. Provide a text prompt, a target language (en, zh, es, ja, ko, fr), and a...

📝 → 🔊 • text-to-speech • voice-cloning • 786 runs

🤖 Model 📝 → 🔊

jichengdu/llasa

Convert text to speech with zero-shot voice cloning from a reference audio sample. Accepts text and a voice sample and o...

📝 → 🔊 • text-to-speech • voice-cloning • chinese-english • 89 runs

🤖 Model 📝 → 🔊

lucataco/csm-1b

Generate conversational speech from text input. Convert text to spoken audio with Sesame’s CSM 1B; choose between two sp...

📝 → 🔊 • text-to-speech • 969 runs

🤖 Model 📝 → 🔊

lucataco/xtts-v2

Clones voices and generates speech in multiple languages from text input and a reference audio sample. Takes text and an...

📝 → 🔊 • text-to-speech • voice-cloning • 7.2M runs

🤖 Model 📝 → 🔊

ttsds/xtts_2

Generate speech from text while cloning a target voice from a reference audio sample. Input text and a speaker reference...

📝 → 🔊 • text-to-speech • voice-cloning • 99 runs

🤖 Model 📝 → 🔊

lucataco/pheme

Generate conversational speech for phone-call applications from text input. Select from multiple preset voices (male_voi...

📝 → 🔊 • text-to-speech • telephony • 557 runs

🤖 Model 📝 → 🔊

jigsawstack/tts

Generate speech audio from text input with low latency. Select from 700+ multilingual voices and accents, or use a voice...

📝 → 🔊 • text-to-speech • voice-cloning • 122 runs

🤖 Model 📝 → 🔊

resemble-ai/chatterbox-pro

Generate expressive speech from text. Accepts a text prompt and returns spoken audio with controllable emotion and proso...

📝 → 🔊 • text-to-speech • 14.6K runs

🤖 Model 📝 → 🔊

thomcle/chatterbox-tts

Convert text to speech with optional zero-shot voice cloning from a short reference audio clip. Accepts text and an opti...

📝 → 🔊 • text-to-speech • voice-cloning • 1.0K runs

🤖 Model 📝 → 🔊

pollinations/bark

Generates speech and audio from text prompts using a transformer-based model. Supports multilingual speech generation wi...

📝 → 🔊 • text-to-speech • music-generation • sound-effect-generation • 1.2K runs

🤖 Model 📝 → 🔊

suno-ai/bark

Generate speech, music, background noise, and simple sound effects from a text prompt. Output an audio file, with an opt...

📝 → 🔊 • text-to-speech • music-generation • sound-effect-generation • 302.0K runs

🤖 Model 📝 → 🔊

chenxwh/openvoice

Clone a voice from a short reference clip and generate speech from text. Accepts text and a reference audio sample; outp...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual • 77.8K runs

🤖 Model 📝 → 🔊

jaaari/kokoro-82m

Generate speech audio from text with selectable multilingual voices. Accepts text input, a preset voice, and a speed mul...

📝 → 🔊 • text-to-speech • multilingual-tts • 53.2M runs

🤖 Model 📝 → 🔊

lucataco/orpheus-3b-0.1-ft

Generate expressive speech from text. Accepts text input and outputs spoken audio, with preset voices (tara, dan, josh,...

📝 → 🔊 • text-to-speech • 30.0K runs