open-standards/aac/aac-rs/tools/voices/samples/index.json
Transaction Science d9e0f89b89
Some checks failed
standards workspaces build + test / jouleclaw-rs (push) Successful in 3m1s
standards workspaces build + test / aac-rs (push) Successful in 1m24s
standards workspaces build + test / joule-code-rs (push) Successful in 54s
standards workspaces build + test / joulecontract-rs (push) Successful in 59s
no-vanity-metrics / Scan committed Markdown for vanity metrics (push) Successful in 4s
standards workspaces build + test / map-rs (push) Successful in 1m8s
standards workspaces build + test / mesh-rs (push) Successful in 40s
standards workspaces build + test / eoc-rs (push) Successful in 1m49s
standards workspaces build + test / jcp-rs (push) Successful in 1m25s
standards workspaces build + test / openpay (push) Successful in 3m24s
standards workspaces build + test / proof-rs (push) Successful in 1m16s
standards workspaces build + test / sandbox-rs (push) Successful in 2m9s
standards workspaces build + test / smart-byte-rs (push) Successful in 2m36s
standards workspaces build + test / arl-rs (push) Has been cancelled
standards workspaces build + test / joule-ui-rs (push) Has been cancelled
standards workspaces build + test / jouledesk-rs (push) Has been cancelled
standards workspaces build + test / joulehook-rs (push) Has been cancelled
standards workspaces build + test / sense-rs (push) Has been cancelled
standards workspaces build + test / macOS energy backend (jcp-energy) (push) Has been cancelled
feat(aac voices): hear a voice before downloading it; ratings measured
A better voice is a 100 MB download, and the person could not hear
one before deciding. Making the samples showed something worse: some
voices did not say the words at all.

- Samples: each voice says a greeting and a request in its language
  (two or three seconds, MP3, about 10 KB). Settings > Better voices
  plays it with the sentence written beside it, before any download;
  checked by size and SHA-256 and played through the voices' own
  output. render_samples.mjs renders them with LAME; they are
  committed (Piper's synthesis is not repeatable), and build_voices.py
  publishes each beside the voices while it says the current text.
- Intelligibility: intelligibility.py has every voice say seven
  everyday phrases, a speech recognizer (Whisper large-v3-turbo on MLX)
  writes down what it hears, and the scores are committed. Ratings now
  come from that evidence (RATING_RULE): under 0.80 the voice is
  withheld; under 0.90, or any phrase under 0.60, experimental; 0.90
  and over clear; 0.95 and over with an upstream grade of A or B,
  natural.
- Withheld, because they say other words: German (the only German
  voice, 0.14), Dutch MLS (0.27), Ukrainian (0.18) and both Japanese
  voices (0.63-0.69: they misread 外, 好き and 疲れた). Their languages
  say so plainly under "Why". Portuguese and Hindi are experimental;
  Spanish, Chinese, Italian, Flemish and Cori are clear; Heart, Emma
  and Siwis natural. 16 voices in 8 languages, 452 MB of packs.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-30 20:20:25 -04:00

114 lines
5.6 KiB
JSON

{
"en-kokoro-af_heart": {
"text": "Hi! Could I have some more juice, please?",
"sha256": "b66c9087db4c7048abcaedda3dc33c6d05bcccc1ee529ebed02a8080b143a694",
"bytes": 10272,
"seconds": 2.5,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"en-kokoro-am_michael": {
"text": "Hi! Could I have some more juice, please?",
"sha256": "f9f2c8961f42631842fa838ce73ee16bfd30ccc660164718bb2dc47dd2659d92",
"bytes": 12384,
"seconds": 3.02,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"en-kokoro-bf_emma": {
"text": "Hi! Could I have some more juice, please?",
"sha256": "e687d39d882375c184aac583e8b1b270aab12d8348aca6153b127ac93fb71317",
"bytes": 12096,
"seconds": 2.98,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"en-piper-cori": {
"text": "Hi! Could I have some more juice, please?",
"sha256": "16165db3d7776ce1914ae63355a7a46f4616f10a50d14d7197919e5912c61b40",
"bytes": 8832,
"seconds": 2.14,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"es-kokoro-ef_dora": {
"text": "¡Hola! Quiero más jugo, por favor.",
"sha256": "c04700d37d5f118c583c04982a10f9f2bed11314eed9bb158c06f7bc5f1ca0f9",
"bytes": 9504,
"seconds": 2.33,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"es-kokoro-em_alex": {
"text": "¡Hola! Quiero más jugo, por favor.",
"sha256": "8bf7b811ec2875a31a2ce7659ba964a7b27715fe67a5ad43d7c8f58f026ce489",
"bytes": 9792,
"seconds": 2.4,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"fr-kokoro-ff_siwis": {
"text": "Bonjour ! Je voudrais encore un peu de jus, s'il vous plaît.",
"sha256": "b52891911edf4e05d181ee11f40abd99d7cd00267c531078ad335ca4ab2c2372",
"bytes": 14880,
"seconds": 3.65,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"hi-kokoro-hf_alpha": {
"text": "नमस्ते! कृपया मुझे और जूस दीजिए।",
"sha256": "ac4c01e098e43a9b3c92cc5b6e5de4fcbe8f853aa75c1315e8bc755ad5d915d9",
"bytes": 15168,
"seconds": 3.73,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"hi-kokoro-hm_omega": {
"text": "नमस्ते! कृपया मुझे और जूस दीजिए।",
"sha256": "9d20d970da6454782e486ca6c0caeb907be3f547642c811a39cbce9140917007",
"bytes": 14784,
"seconds": 3.63,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"it-kokoro-if_sara": {
"text": "Ciao! Vorrei ancora un po' di succo, per favore.",
"sha256": "9c187a5a095c3bc4d4ab9e2c366a5a0e4f423ca34a56fc33a2882cadb4142f5f",
"bytes": 12960,
"seconds": 3.17,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"it-kokoro-im_nicola": {
"text": "Ciao! Vorrei ancora un po' di succo, per favore.",
"sha256": "e4292e40fd83e1a1505c3124919d706cf89808d2c8da807943aa5a324d597f0e",
"bytes": 13152,
"seconds": 3.23,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"nl-piper-rdh": {
"text": "Hallo! Mag ik nog wat sap, alsjeblieft?",
"sha256": "0c5eca7eff946c95179bdde32e11292c3de00e3044d69867e0ac74f1fd0d4036",
"bytes": 11232,
"seconds": 2.75,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"pt-kokoro-pf_dora": {
"text": "Olá! Eu queria mais suco, por favor.",
"sha256": "6506192f279006c140bad68d07c0b41a0e01692a0cb382c43aa22fae097c7e19",
"bytes": 11232,
"seconds": 2.75,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"pt-kokoro-pm_alex": {
"text": "Olá! Eu queria mais suco, por favor.",
"sha256": "de8be0ebeb9b652c625f4cf12dd0cb3f3b8839a9bb8173578d86f10c08f4dcfe",
"bytes": 11040,
"seconds": 2.7,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"zh-kokoro-zf_xiaobei": {
"text": "你好!请再给我一些果汁,谢谢。",
"sha256": "e049569f81b2746091e0505cb16f46ce42f1384a643d2e91370c701d5a2718f6",
"bytes": 15936,
"seconds": 3.92,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
},
"zh-kokoro-zm_yunjian": {
"text": "你好!请再给我一些果汁,谢谢。",
"sha256": "e90e6b133b9103685027e275803619a873f46912e248a0c27d76f93f79730539",
"bytes": 14496,
"seconds": 3.58,
"tool": "LAME 64bits version 4.0 (https://lame.sourceforge.io): --quiet -m m -b 32 --resample 24 --noreplaygain -q 0; peak limited to 0.89"
}
}