{ "family": "pocket_tts", "display_name": "PocketTTS", "description": "Kyutai 100M-parameter CPU-friendly TTS package set for real-time local synthesis and small-footprint voice cloning in English, German, Italian, Portuguese, and Spanish.", "category": "tts", "status": "supported", "tasks": [ "tts", "clone" ], "modes": [ "offline" ], "languages": [ "en", "de", "it", "pt", "es" ], "capabilities": { "clone": [ "speaker_reference" ] }, "runtime": { "tags": [ "gguf" ] }, "ui": { "recommended_package": "pocket_tts_english_q8_0", "tags": [ "TTS", "Clone", "GGUF" ], "docs": [ "docs/tts.md", "docs/gguf.md" ] }, "package_defaults": { "download": { "kind": "huggingface_snapshot", "repo": "audio-cpp/audio.cpp-gguf", "revision": "main", "gated": false } }, "packages": [ { "id": "pocket_tts_english_q8_0", "display_name": "PocketTTS English Q8_0 GGUF", "default": true, "format": "gguf", "precision": "q8_0", "target_directory": "PocketTTS-GGUF/english", "files": [ "PocketTTS-GGUF/english/pocket-tts-english-q8_0.gguf" ], "strip_prefix": "PocketTTS-GGUF/english" }, { "id": "pocket_tts_english_bf16", "display_name": "PocketTTS English BF16 GGUF", "format": "gguf", "precision": "bf16", "target_directory": "PocketTTS-GGUF/english", "files": [ "PocketTTS-GGUF/english/pocket-tts-english-bf16.gguf" ], "strip_prefix": "PocketTTS-GGUF/english" }, { "id": "pocket_tts_german_q8_0", "display_name": "PocketTTS German Q8_0 GGUF", "format": "gguf", "precision": "q8_0", "target_directory": "PocketTTS-GGUF/german", "files": [ "PocketTTS-GGUF/german/pocket-tts-german-q8_0.gguf" ], "strip_prefix": "PocketTTS-GGUF/german" }, { "id": "pocket_tts_german_bf16", "display_name": "PocketTTS German BF16 GGUF", "format": "gguf", "precision": "bf16", "target_directory": "PocketTTS-GGUF/german", "files": [ "PocketTTS-GGUF/german/pocket-tts-german-bf16.gguf" ], "strip_prefix": "PocketTTS-GGUF/german" }, { "id": "pocket_tts_italian_q8_0", "display_name": "PocketTTS Italian Q8_0 GGUF", "format": "gguf", "precision": "q8_0", "target_directory": "PocketTTS-GGUF/italian", "files": [ "PocketTTS-GGUF/italian/pocket-tts-italian-q8_0.gguf" ], "strip_prefix": "PocketTTS-GGUF/italian" }, { "id": "pocket_tts_italian_bf16", "display_name": "PocketTTS Italian BF16 GGUF", "format": "gguf", "precision": "bf16", "target_directory": "PocketTTS-GGUF/italian", "files": [ "PocketTTS-GGUF/italian/pocket-tts-italian-bf16.gguf" ], "strip_prefix": "PocketTTS-GGUF/italian" }, { "id": "pocket_tts_portuguese_q8_0", "display_name": "PocketTTS Portuguese Q8_0 GGUF", "format": "gguf", "precision": "q8_0", "target_directory": "PocketTTS-GGUF/portuguese", "files": [ "PocketTTS-GGUF/portuguese/pocket-tts-portuguese-q8_0.gguf" ], "strip_prefix": "PocketTTS-GGUF/portuguese" }, { "id": "pocket_tts_portuguese_bf16", "display_name": "PocketTTS Portuguese BF16 GGUF", "format": "gguf", "precision": "bf16", "target_directory": "PocketTTS-GGUF/portuguese", "files": [ "PocketTTS-GGUF/portuguese/pocket-tts-portuguese-bf16.gguf" ], "strip_prefix": "PocketTTS-GGUF/portuguese" }, { "id": "pocket_tts_spanish_q8_0", "display_name": "PocketTTS Spanish Q8_0 GGUF", "format": "gguf", "precision": "q8_0", "target_directory": "PocketTTS-GGUF/spanish", "files": [ "PocketTTS-GGUF/spanish/pocket-tts-spanish-q8_0.gguf" ], "strip_prefix": "PocketTTS-GGUF/spanish" }, { "id": "pocket_tts_spanish_bf16", "display_name": "PocketTTS Spanish BF16 GGUF", "format": "gguf", "precision": "bf16", "target_directory": "PocketTTS-GGUF/spanish", "files": [ "PocketTTS-GGUF/spanish/pocket-tts-spanish-bf16.gguf" ], "strip_prefix": "PocketTTS-GGUF/spanish" }, { "id": "pocket_tts_english_safetensors", "display_name": "PocketTTS English Safetensors", "format": "safetensors", "precision": "native", "target_directory": "pocket-tts", "files": [ "languages/english/embeddings/alba.safetensors", "languages/english/embeddings/anna.safetensors", "languages/english/embeddings/azelma.safetensors", "languages/english/embeddings/bill_boerst.safetensors", "languages/english/embeddings/caro_davy.safetensors", "languages/english/embeddings/charles.safetensors", "languages/english/embeddings/cosette.safetensors", "languages/english/embeddings/eponine.safetensors", "languages/english/embeddings/estelle.safetensors", "languages/english/embeddings/eve.safetensors", "languages/english/embeddings/fantine.safetensors", "languages/english/embeddings/george.safetensors", "languages/english/embeddings/giovanni.safetensors", "languages/english/embeddings/jane.safetensors", "languages/english/embeddings/javert.safetensors", "languages/english/embeddings/jean.safetensors", "languages/english/embeddings/juergen.safetensors", "languages/english/embeddings/lola.safetensors", "languages/english/embeddings/marius.safetensors", "languages/english/embeddings/mary.safetensors", "languages/english/embeddings/michael.safetensors", "languages/english/embeddings/paul.safetensors", "languages/english/embeddings/peter_yearsley.safetensors", "languages/english/embeddings/rafael.safetensors", "languages/english/embeddings/stuart_bell.safetensors", "languages/english/embeddings/vera.safetensors", "languages/english/model.safetensors", "languages/english/tokenizer.model" ], "download": { "kind": "huggingface_snapshot", "repo": "kyutai/pocket-tts" } } ], "sources": [ { "format": "gguf", "roots": { "model": ".", "weights": "$gguf" }, "files": { "tokenizer": "model:tokenizer.model" }, "optional_files": { "config": "model:config.yaml" }, "tensors": { "weights": "weights:" } }, { "format": "safetensors", "roots": { "language": "languages/english" }, "files": { "tokenizer": "language:tokenizer.model" }, "optional_files": { "config": "language:config.yaml" }, "tensors": { "weights": "language:model.safetensors" } } ] }