multilingual AI Models

🤖 Model 📝 → 🖼️

ideogram-ai/ideogram-v2a

Generates images from text prompts with specialized text rendering capabilities. Excels at creating designs, logos, and...

📝 → 🖼️ • text-to-image • logo-design • 2.1M runs

🤖 Model 📝 → 🔊

elevenlabs/turbo-v2.5

Convert text to speech audio with low latency for real-time voice agents, chatbots, and interactive apps. Generate multi...

📝 → 🔊 • text-to-speech • multilingual • real-time • 26 runs

🤖 Model 📝 → 🔊

elevenlabs/flash-v2.5

Convert text to speech with ultra-low latency for real-time voice agents, chatbots, and interactive apps. Accepts text p...

📝 → 🔊 • text-to-speech • multilingual • real-time • 330 runs

🤖 Model 📝 → 📝

lucataco/qwen1.5-4b

Generate and chat in multiple languages from text prompts. Accepts a user prompt and optional system prompt and returns...

📝 → 📝 • text-generation • multilingual • code-generation • 1.4K runs

🤖 Model 📝 → 🖼️

wavespeedai/qwen-image

Generate images from text prompts with native, in-pixel text rendering. Accepts a prompt and optional aspect ratio (1:1,...

📝 → 🖼️ • text-to-image • poster-design • multilingual • 8.0K runs

🤖 Model

subformer/meta-omnilingual-asr-7b

Transcribe speech to text from short audio clips in 1,693 languages. Accept audio input and optionally a specified langu...

speech-to-text • multilingual • language-detection • 2 runs

🤖 Model 📝 → 🔊

qwen/qwen-tts

Generate speech from text with preset, cloned, or designed voices. Accept text as input and return spoken audio. Choose...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual • 9 runs

🤖 Model

light770/qwen3-embedding-0.6b

Convert text to vector embeddings for semantic search, RAG, and pgvector-based retrieval. Accepts a string or an array o...

text-embedding • multilingual • 1 runs

🤖 Model

ditto--ai/qwen3guard-gen-4b

Moderate text by classifying user prompts and optional assistant responses as Safe, Unsafe, or Controversial. Accepts a...

text-moderation • content-moderation • multilingual • 361.8K runs

🤖 Model 📝 → 🔊

qwen/qwen3-tts

Generate multilingual speech from text with preset voices, voice cloning, and voice design. Accept text plus optional la...

📝 → 🔊 • text-to-speech • voice-cloning • multilingual • 216.6K runs

🤖 Model 📝 → 🔊

minimax/speech-2.8-turbo

Generate speech audio from text input. Control emotion (neutral, happy, sad, angry, fearful, disgusted, surprised, calm,...

📝 → 🔊 • text-to-speech • multilingual • 1 runs

🤖 Model 📝 → 🔊

inworld/tts-1.5-max

Converts text to natural, expressive speech with low latency under 200ms. Supports 15 languages including English, Chine...

📝 → 🔊 • text-to-speech • voice-cloning • 79.5K runs

🤖 Model 📝 → 🔊

inworld/tts-1.5-mini

Converts text to speech with ultra-fast ~120ms latency and support for 15 languages including English, Chinese, Japanese...

📝 → 🔊 • text-to-speech • voice-cloning • 30.2K runs

🤖 Model 📝 → 📝

lucataco/ollama-qwen2.5-72b

Generates text responses based on input prompts using the Qwen2.5 72B instruction-tuned language model. Supports text ge...

📝 → 📝 • text-generation • code-generation • question-answering • 27.4K runs

🤖 Model 📝 → 🎥

wan-video/wan-2.5-t2v-fast

Generates videos with synchronized audio from text prompts, optimized for faster generation times compared to the standa...

📝 → 🎥 • text-to-video-with-audio • multilingual • 49.9K runs

🤖 Model 🖼️ → 📝

prunaai/gemma-4-26b-a4b-fast

Generates text responses from text, image, and video inputs using a multimodal reasoning model. Processes questions abou...

🖼️ → 📝 • text-generation • image-to-text • video-to-text • 14.1K runs

🤖 Model 🖼️ → 📝

prunaai/qwen-3.5-35b-a3b-fast

Generates text responses from text, image, and video inputs using a 35B-parameter multimodal reasoning model optimized b...

🖼️ → 📝 • text-generation • image-to-text • video-to-text • 57 runs