Muna
Muna Logo
Explore
Docs
Pricing
Blog
Careers
Sign Up

Explore Models

Text to Speech1 model

Models compatible with openai.audio.speech.create(...)

  • @kitten-ml/kitten-tts

    Perform text-to-speech with Kitten TTS.

Embeddings1 model

Models compatible with openai.embeddings.create(...)

  • @google/embedding-gemma

    Create embedding vectors from text with EmbeddingGemma.

Other Models31 models

Models with custom APIs

View all
  • @bytedance/depth-anything-large

    Estimate metric depth from an image using Depth Anything (large).

  • @bytedance/depth-anything-v2-small

    Estimate metric depth from an image with Depth Anything V2 (small).

  • @bytedance/depth-anything-v3-metric-large

    Estimate metric depth from a monocular image with Depth Anything V3 (metric large).

  • @mediapipe/blazepose-landmarks-lite

    Infer the full body pose an from RoI with BlazePose Landmarks (lite).

  • @mediapipe/blazepose-detector-lite

    Detect pose ROIs in an image with BlazePose Detector (lite).

  • @roboflow/rf-detr

    Detect objects in an image with RF-DETR.

Show 25 more

Footer

TwitterGitHubSlackSlack

© 2026 NatML Inc. All rights reserved.