{"data":{"slug":"nari-labs-dia","name":"dia","tagline":"A TTS model for generating ultra-realistic dialogue","github_url":"https://github.com/nari-labs/dia","owner":"nari-labs","repo":"dia","owner_avatar_url":"https://avatars.githubusercontent.com/u/208232306?v=4","primary_language":"Python","stars":19361,"forks":1688,"topics":["ai","open-weight","text-to-speech"],"archived":false,"github_pushed_at":"2025-11-19T21:11:55+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/nari-labs-dia","markdown_url":"https://www.graphcanon.com/tools/nari-labs-dia.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nari-labs-dia","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nari-labs-dia","description":"A TTS model capable of generating ultra-realistic dialogue in one pass.","homepage_url":null,"license":"Apache-2.0","open_issues":91,"watchers":162,"ai_summary":"Dia is an open-weight text-to-dialogue model that allows full control over scripts and voices.","readme_excerpt":"# or install with uv\nuv pip install git+https://github.com/huggingface/transformers.git\n```\n\nRun `hf.py`. The file is as below.\n\n```python\nfrom transformers import AutoProcessor, DiaForConditionalGeneration\n\n\ntorch_device = \"cuda\"\nmodel_checkpoint = \"nari-labs/Dia-1.6B-0626\"\n\ntext = [\n    \"[S1] Dia is an open weights text to dialogue model. [S2] You get full control over scripts and voices. [S1] Wow. Amazing. (laughs) [S2] Try it now on Git hub or Hugging Face.\"\n]\nprocessor = AutoProcessor.from_pretrained(model_checkpoint)\ninputs = processor(text=text, padding=True, return_tensors=\"pt\").to(torch_device)\n\nmodel = DiaForConditionalGeneration.from_pretrained(model_checkpoint).to(torch_device)\noutputs = model.generate(\n    **inputs, max_new_tokens=3072, guidance_scale=3.0, temperature=1.8, top_p=0.90, top_k=45\n)\n\noutputs = processor.batch_decode(outputs)\nprocessor.save_audio(outputs, \"example.mp3\")\n```\n\n</details>\n\n---\n\n# Install dia\npip install -e .\n```\n\nOr you can install without cloning.\n\n```bash\n\n---\n\n# Install directly from GitHub\npip install git+https://github.com/nari-labs/dia.git\n```\n\nNow, run some examples.\n\n```bash\npython example/simple.py\n```\n</details>\n\n\n<details>\n<summary>Install via uv</summary>\n\nYou need [uv](https://docs.astral.sh/uv/) to be installed.\n\n```bash\n\n---\n\n## 💻 Hardware and Inference Speed\n\nDia has been tested on only GPUs (pytorch 2.0+, CUDA 12.6). CPU support is to be added soon.\nThe initial run will take longer as the Descript Audio Codec also needs to be downloaded.\n\nThese are the speed we benchmarked in RTX 4090.\n\n| precision | realtime factor w/ compile | realtime factor w/o compile | VRAM |\n|:-:|:-:|:-:|:-:|\n| `bfloat16` | x2.1 | x1.5 | ~4.4GB |\n| `float16` | x2.2 | x1.3 | ~4.4GB |\n| `float32` | x1 | x0.9 | ~7.9GB |\n\nWe will be adding a quantized version in the future.\n\nIf you don't have hardware available or if you want to play with bigger versions of our models, join the waitlist [here](https://tally.so/r/meokbo).\n\n---\n\n## 🪪 License\n\nThis project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.","github_created_at":"2025-04-19T07:15:57+00:00","created_at":"2026-07-11T12:04:07.027833+00:00","updated_at":"2026-07-29T06:00:14.901726+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"dialogue-generation","name":"dialogue-generation"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"tts","name":"tts"}],"trust":{"provenance":{"is_fork":false,"github_id":969010919,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-29T06:00:14.145Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":251,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:04:13.638Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-29T06:00:14.596Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-29T06:00:14.596Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-29T06:00:14.596Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you require precise control over voice and script in the creation of highly realistic dialogues","If your project involves GPU acceleration and you prefer working with CUDA-supported platforms like Pytorch 2.0+"],"when_not_to_use":["If your setup lacks a GPU, as Dia has not yet added CPU support","In scenarios where immediate real-time performance is critical since the first run could be longer due to additional codec downloads"],"source":"enrich:decision_facts","observed_at":"2026-07-17T13:14:32.579Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Dia is an open-weight text-to-dialogue model providing full control over scripts and voices, ideal for generating ultra-realistic dialogue."}]}}