liqiang/ai-agent-book
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
Build latest book artifacts / build (push) Canceled after 0s
Details
dependency resolution / resolve (3.11) (push) Canceled after 0s
Details
dependency resolution / resolve (3.13) (push) Canceled after 0s
Details
deploy-pages / build (push) Canceled after 0s
Details
deploy-pages / deploy (push) Canceled after 0s
Details
i18n consistency check / check (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
Details
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
Details
web-search-agent tests / test (push) Canceled after 0s
Details
web-search-agent tests / agentbook (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
liqiang
2026-08-20 13:12:50 +00:00
commit b119135836
10275 changed files with 3284984 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
chapter6/controllable-tts/validation/acceptance.json
+404
View File
@@ -0,0 +1,404 @@
{
"schema_version": 3,
"experiment": "6-6",
"timestamp_utc": "2026-07-30T05:30:13.308665+00:00",
"artifact_generation": {
"recorded_timestamp_utc": "2026-07-29T10:19:56.497167+00:00",
"provider": "Fish Audio",
"backend": "s1",
"source_reference_id_sha256": "bb2ec197d6276bfad81bbdbcec4473040861e6bc20caf53cf4d1f8184a7416be",
"source_reference_value_saved_in_manifest": true,
"estimated_paid_api_requests": 30,
"request_count_basis": "24 reference renders + A(1) + B(1) + C(4 speech segments); local silence is not an API call",
"provider_reported_cost_usd": null,
"cost_note": "Fish SDK responses did not expose monetary charges; consult the provider billing ledger."
},
"validation_provenance": {
"platform": "macOS-26.3-arm64-arm-64bit",
"python": "3.11.4",
"manifest_sha256": "24f6e1399376665f7f5c0282dbb77d81aa5e124cfb9df944b46b73692e4b5ad1",
"run_evidence_sha256": "de0e787c940cf387ac7dabb03125893deffb9eedb2c5f25d72654fe6829815c1",
"implementation_sha256": {
"demo.py": "73a87e6020910cc3b43a6ae7291defe39d9c715a964a04e8a674c4d0e4d02fe9",
"tts.py": "e7ce66c0aa2fc3b7a78530001623e5c68b78a5bf37aa97eb77203312f5a4b0c9",
"markup.py": "5230a2a178cedfe9b5b8d79e80912ce8aa6326a8e2e7d7fdda1b670c49c843ad",
"voice_library.py": "c1fb6720742ae49677226dab85ad2bf580e137ee040ba17c8730399fc6a5fd70",
"evaluate_audio_quality.py": "4fedd536432702c7d4eec9360fb3671461648ee5f316a494f55fafdc29fcafa1"
}
},
"reference_statistics": {
"count": 24,
"minimum_duration_seconds": 3.604813,
"maximum_duration_seconds": 6.7395,
"mean_duration_seconds": 4.858690416666666
},
"reference_checks": [
{
"profile": "frustrated_fast_casual",
"path": "reference_audio/frustrated_fast_casual.mp3",
"exists": true,
"sha256": "6d427ddd6874b1b80b18e0129712ca100865e3592efa0e142904f160305686da",
"manifest_sha256": "6d427ddd6874b1b80b18e0129712ca100865e3592efa0e142904f160305686da",
"hash_matches": true,
"duration_seconds": 5.355,
"size_bytes": 85680,
"format": "mp3"
},
{
"profile": "frustrated_fast_formal",
"path": "reference_audio/frustrated_fast_formal.mp3",
"exists": true,
"sha256": "3c64faf47685da3e3ba08b93b48baf32249dbf074421f577ebb3b3da16d815f2",
"manifest_sha256": "3c64faf47685da3e3ba08b93b48baf32249dbf074421f577ebb3b3da16d815f2",
"hash_matches": true,
"duration_seconds": 5.61625,
"size_bytes": 89860,
"format": "mp3"
},
{
"profile": "frustrated_normal_casual",
"path": "reference_audio/frustrated_normal_casual.mp3",
"exists": true,
"sha256": "23cefb4913ba3a3a8ea78a9b221b3e88754e0d10166d382e947dcfa16aef9c2c",
"manifest_sha256": "23cefb4913ba3a3a8ea78a9b221b3e88754e0d10166d382e947dcfa16aef9c2c",
"hash_matches": true,
"duration_seconds": 4.701938,
"size_bytes": 75231,
"format": "mp3"
},
{
"profile": "frustrated_normal_formal",
"path": "reference_audio/frustrated_normal_formal.mp3",
"exists": true,
"sha256": "8f510ebb97a2e31315029934015a109a438041870d651e7b078e9165746f4b6a",
"manifest_sha256": "8f510ebb97a2e31315029934015a109a438041870d651e7b078e9165746f4b6a",
"hash_matches": true,
"duration_seconds": 4.858688,
"size_bytes": 77739,
"format": "mp3"
},
{
"profile": "frustrated_slow_casual",
"path": "reference_audio/frustrated_slow_casual.mp3",
"exists": true,
"sha256": "490c56a2dbc01f08380693173af76e0fcb48dfb24e29f5f828f7709cbc67faf2",
"manifest_sha256": "490c56a2dbc01f08380693173af76e0fcb48dfb24e29f5f828f7709cbc67faf2",
"hash_matches": true,
"duration_seconds": 3.604813,
"size_bytes": 57677,
"format": "mp3"
},
{
"profile": "frustrated_slow_formal",
"path": "reference_audio/frustrated_slow_formal.mp3",
"exists": true,
"sha256": "aab5806b6b7bfb17d9d2a069b8b1fb19f01cdc026e04f2e28dc92be94940b575",
"manifest_sha256": "aab5806b6b7bfb17d9d2a069b8b1fb19f01cdc026e04f2e28dc92be94940b575",
"hash_matches": true,
"duration_seconds": 4.545188,
"size_bytes": 72723,
"format": "mp3"
},
{
"profile": "happy_fast_casual",
"path": "reference_audio/happy_fast_casual.mp3",
"exists": true,
"sha256": "0e96b8c6abe891c6292e6c7037aac67979ac407c3125301f5421afe35ce256d5",
"manifest_sha256": "0e96b8c6abe891c6292e6c7037aac67979ac407c3125301f5421afe35ce256d5",
"hash_matches": true,
"duration_seconds": 4.963188,
"size_bytes": 79411,
"format": "mp3"
},
{
"profile": "happy_fast_formal",
"path": "reference_audio/happy_fast_formal.mp3",
"exists": true,
"sha256": "d3993a35b54c843c3a8d6470d8754f1b3344c60b460b9d11b6141761de31f987",
"manifest_sha256": "d3993a35b54c843c3a8d6470d8754f1b3344c60b460b9d11b6141761de31f987",
"hash_matches": true,
"duration_seconds": 6.7395,
"size_bytes": 107832,
"format": "mp3"
},
{
"profile": "happy_normal_casual",
"path": "reference_audio/happy_normal_casual.mp3",
"exists": true,
"sha256": "c374978ccaf9947ffc1b52a17ecf29cc904e8753e4fe0336b7c2aefee1b0af1e",
"manifest_sha256": "c374978ccaf9947ffc1b52a17ecf29cc904e8753e4fe0336b7c2aefee1b0af1e",
"hash_matches": true,
"duration_seconds": 5.067688,
"size_bytes": 81083,
"format": "mp3"
},
{
"profile": "happy_normal_formal",
"path": "reference_audio/happy_normal_formal.mp3",
"exists": true,
"sha256": "e0c6d9b5402d9ed7cc1375411951c22f09bd118a88e5abfc96bf67a3b1d76ba1",
"manifest_sha256": "e0c6d9b5402d9ed7cc1375411951c22f09bd118a88e5abfc96bf67a3b1d76ba1",
"hash_matches": true,
"duration_seconds": 5.119938,
"size_bytes": 81919,
"format": "mp3"
},
{
"profile": "happy_slow_casual",
"path": "reference_audio/happy_slow_casual.mp3",
"exists": true,
"sha256": "014864a698f1da3988895936238f0e538215d0fe4b0140c17d0eb339f0b23c02",
"manifest_sha256": "014864a698f1da3988895936238f0e538215d0fe4b0140c17d0eb339f0b23c02",
"hash_matches": true,
"duration_seconds": 4.310125,
"size_bytes": 68962,
"format": "mp3"
},
{
"profile": "happy_slow_formal",
"path": "reference_audio/happy_slow_formal.mp3",
"exists": true,
"sha256": "29545d9cc2fc4bba11dd9d4567569acdc96486317d86c665940833df333a2696",
"manifest_sha256": "29545d9cc2fc4bba11dd9d4567569acdc96486317d86c665940833df333a2696",
"hash_matches": true,
"duration_seconds": 5.067688,
"size_bytes": 81083,
"format": "mp3"
},
{
"profile": "neutral_fast_casual",
"path": "reference_audio/neutral_fast_casual.mp3",
"exists": true,
"sha256": "961886b92e69da009d07e9ea9a0c0f8d67050d378fb2ffd50850876ebcd6ba16",
"manifest_sha256": "961886b92e69da009d07e9ea9a0c0f8d67050d378fb2ffd50850876ebcd6ba16",
"hash_matches": true,
"duration_seconds": 5.172125,
"size_bytes": 82754,
"format": "mp3"
},
{
"profile": "neutral_fast_formal",
"path": "reference_audio/neutral_fast_formal.mp3",
"exists": true,
"sha256": "58870daca86d21ca7f8a785342ade7212358537cc67bc7168d4f9cb82df1465a",
"manifest_sha256": "58870daca86d21ca7f8a785342ade7212358537cc67bc7168d4f9cb82df1465a",
"hash_matches": true,
"duration_seconds": 5.146063,
"size_bytes": 82337,
"format": "mp3"
},
{
"profile": "neutral_normal_casual",
"path": "reference_audio/neutral_normal_casual.mp3",
"exists": true,
"sha256": "5849473deb7f0415a57fa96e5365e76e5850a9c5c598c3926c9f4feba77d1ce5",
"manifest_sha256": "5849473deb7f0415a57fa96e5365e76e5850a9c5c598c3926c9f4feba77d1ce5",
"hash_matches": true,
"duration_seconds": 4.205625,
"size_bytes": 67290,
"format": "mp3"
},
{
"profile": "neutral_normal_formal",
"path": "reference_audio/neutral_normal_formal.mp3",
"exists": true,
"sha256": "2cf4c64bb8222399ab54c63cc41049c572ea5f1b819ffdcbc496014daae004c0",
"manifest_sha256": "2cf4c64bb8222399ab54c63cc41049c572ea5f1b819ffdcbc496014daae004c0",
"hash_matches": true,
"duration_seconds": 4.623563,
"size_bytes": 73977,
"format": "mp3"
},
{
"profile": "neutral_slow_casual",
"path": "reference_audio/neutral_slow_casual.mp3",
"exists": true,
"sha256": "6599f401b009ad55c5c17b4509d21a7ca4c83af50bf9e1c036ad496d015a966f",
"manifest_sha256": "6599f401b009ad55c5c17b4509d21a7ca4c83af50bf9e1c036ad496d015a966f",
"hash_matches": true,
"duration_seconds": 4.545188,
"size_bytes": 72723,
"format": "mp3"
},
{
"profile": "neutral_slow_formal",
"path": "reference_audio/neutral_slow_formal.mp3",
"exists": true,
"sha256": "fd775e92e16733b8ac90885505293d20c64dcb6f421fec3aaf1eb380561aaf06",
"manifest_sha256": "fd775e92e16733b8ac90885505293d20c64dcb6f421fec3aaf1eb380561aaf06",
"hash_matches": true,
"duration_seconds": 4.466875,
"size_bytes": 71470,
"format": "mp3"
},
{
"profile": "thinking_fast_casual",
"path": "reference_audio/thinking_fast_casual.mp3",
"exists": true,
"sha256": "72de0d846bf47a7754afb2c2bb66e20047d0ca62575d605df63546589a5f2260",
"manifest_sha256": "72de0d846bf47a7754afb2c2bb66e20047d0ca62575d605df63546589a5f2260",
"hash_matches": true,
"duration_seconds": 5.067688,
"size_bytes": 81083,
"format": "mp3"
},
{
"profile": "thinking_fast_formal",
"path": "reference_audio/thinking_fast_formal.mp3",
"exists": true,
"sha256": "5efd200c837b20b123ba019b893fd5d5ad2671188f94478dc66db512455d85ae",
"manifest_sha256": "5efd200c837b20b123ba019b893fd5d5ad2671188f94478dc66db512455d85ae",
"hash_matches": true,
"duration_seconds": 5.146063,
"size_bytes": 82337,
"format": "mp3"
},
{
"profile": "thinking_normal_casual",
"path": "reference_audio/thinking_normal_casual.mp3",
"exists": true,
"sha256": "49f77a6fc84657dbb45498d49aae40a0020fbf615622fcdacee686ff19231f5b",
"manifest_sha256": "49f77a6fc84657dbb45498d49aae40a0020fbf615622fcdacee686ff19231f5b",
"hash_matches": true,
"duration_seconds": 4.754188,
"size_bytes": 76067,
"format": "mp3"
},
{
"profile": "thinking_normal_formal",
"path": "reference_audio/thinking_normal_formal.mp3",
"exists": true,
"sha256": "9637338fcf8cb6d17febbe01b4eedbb06423637163681ca864748ebd29e289de",
"manifest_sha256": "9637338fcf8cb6d17febbe01b4eedbb06423637163681ca864748ebd29e289de",
"hash_matches": true,
"duration_seconds": 4.754188,
"size_bytes": 76067,
"format": "mp3"
},
{
"profile": "thinking_slow_casual",
"path": "reference_audio/thinking_slow_casual.mp3",
"exists": true,
"sha256": "4c1d61c92b4eebc2c050e7b21d138ffac4d7e0ba6449e0f4215db5e93c61d992",
"manifest_sha256": "4c1d61c92b4eebc2c050e7b21d138ffac4d7e0ba6449e0f4215db5e93c61d992",
"hash_matches": true,
"duration_seconds": 4.310125,
"size_bytes": 68962,
"format": "mp3"
},
{
"profile": "thinking_slow_formal",
"path": "reference_audio/thinking_slow_formal.mp3",
"exists": true,
"sha256": "abef0a802382dad67b37e3447de08401a1d1cdb451420759853f4af9df234ac9",
"manifest_sha256": "abef0a802382dad67b37e3447de08401a1d1cdb451420759853f4af9df234ac9",
"hash_matches": true,
"duration_seconds": 4.466875,
"size_bytes": 71470,
"format": "mp3"
}
],
"outputs": {
"A_no_control_markers": {
"path": "output/A_no_control_markers.mp3",
"sha256": "b477ff767fcf7dc01b62bf8f445f79f2445fa204f8b365b437bcdf2e64b647e5",
"duration_seconds": 5.355,
"size_bytes": 85680,
"format": "mp3"
},
"B_single_reference": {
"path": "output/B_single_reference.mp3",
"sha256": "29148f5b08806b12e0a993366e97b172acaa3f754c171eea700f8e03aced58a6",
"duration_seconds": 5.903563,
"size_bytes": 94457,
"format": "mp3"
},
"C_24_reference_library": {
"path": "output/C_24_reference_library.mp3",
"sha256": "5182f816524ebd92150d7ce01bd4be8e3baee2b51479ce64d6b9363140e33f04",
"duration_seconds": 8.305306,
"size_bytes": 133790,
"format": "mp3"
}
},
"qualitative_study": {
"path": "validation/audio_quality_study.json",
"present": true,
"valid": true,
"error": null,
"judge_type": "multimodal_llm_not_human_mos",
"provider": "Mistral Voxtral API",
"model": "voxtral-small-latest",
"aggregate": {
"configurations": {
"A_no_control_markers": {
"dimension_means": {
"naturalness": 4.0,
"expressive_fit": 4.0,
"thinking_behavior": 3.6666666666666665,
"speaker_consistency": 4.0,
"human_customer_service": 4.0
},
"overall_mean": 3.9333333333333327,
"rank_points": 6
},
"B_single_reference": {
"dimension_means": {
"naturalness": 3.3333333333333335,
"expressive_fit": 3.3333333333333335,
"thinking_behavior": 2.6666666666666665,
"speaker_consistency": 3.3333333333333335,
"human_customer_service": 3.3333333333333335
},
"overall_mean": 3.2,
"rank_points": 4
},
"C_24_reference_library": {
"dimension_means": {
"naturalness": 4.666666666666667,
"expressive_fit": 4.666666666666667,
"thinking_behavior": 4.333333333333333,
"speaker_consistency": 4.666666666666667,
"human_customer_service": 4.666666666666667
},
"overall_mean": 4.6000000000000005,
"rank_points": 8
}
},
"aggregate_ranking": [
"C_24_reference_library",
"A_no_control_markers",
"B_single_reference"
],
"expected_manuscript_ranking": [
"C_24_reference_library",
"B_single_reference",
"A_no_control_markers"
],
"manuscript_quality_ordering_reproduced": false,
"near_human_customer_service_supported": true,
"manuscript_quality_claim_reproduced": false
},
"sha256": "8ef0917a2cf801590242fa4a670446835048ccb44a522516f2e0dc879de6e0cb"
},
"acceptance": {
"structural_and_media_gates": {
"fish_s1_provider_recorded": true,
"same_authorized_source_reference": true,
"exact_4x3x2_reference_library": true,
"all_reference_hashes_match": true,
"references_approximately_five_seconds": true,
"three_real_comparison_outputs": true,
"required_marker_routes_exercised": true,
"thinking_pause_1_to_2_seconds": true,
"thinking_native_filler_exercised": true
},
"structural_and_media_passed": true,
"qualitative_listening_study_present": true,
"qualitative_judge_is_human_mos": false,
"near_human_customer_service_claim_evaluated": true,
"manuscript_quality_claim_reproduced": false,
"experiment_execution_complete": true,
"statement": "Real Fish S1 media and a schema-checked, position-balanced multimodal listening study complete the A/B/C experiment. The saved result reports independently whether the manuscript's subjective ordering reproduced; this is not a human MOS panel."
}
}
chapter6/controllable-tts/validation/audio_quality_study.json
+332
View File
@@ -0,0 +1,332 @@
{
"schema_version": 1,
"experiment": "6-6",
"timestamp_utc": "2026-07-30T04:17:59.570927+00:00",
"provider": "Mistral Voxtral API",
"model": "voxtral-small-latest",
"provider_attempts": [],
"study_design": {
"judge_type": "multimodal_llm_not_human_mos",
"blinded_configuration_labels": true,
"position_balanced": true,
"passes": 3,
"temperature": 0.0,
"dimensions": [
"naturalness",
"expressive_fit",
"thinking_behavior",
"speaker_consistency",
"human_customer_service"
]
},
"audio_sha256": {
"A_no_control_markers": "b477ff767fcf7dc01b62bf8f445f79f2445fa204f8b365b437bcdf2e64b647e5",
"B_single_reference": "29148f5b08806b12e0a993366e97b172acaa3f754c171eea700f8e03aced58a6",
"C_24_reference_library": "5182f816524ebd92150d7ce01bd4be8e3baee2b51479ce64d6b9363140e33f04"
},
"passes": [
{
"alias_to_configuration": {
"X": "A_no_control_markers",
"Y": "B_single_reference",
"Z": "C_24_reference_library"
},
"response": {
"clips": {
"X": {
"naturalness": {
"score": 4,
"reason": "The speech flows smoothly with natural intonation and pacing."
},
"expressive_fit": {
"score": 4,
"reason": "The speaker conveys happiness in confirmation and thoughtful consideration in checking the shipping time."
},
"thinking_behavior": {
"score": 4,
"reason": "The pause before checking the shipping time is natural and appropriate."
},
"speaker_consistency": {
"score": 4,
"reason": "The speaker maintains a consistent tone and style throughout the message."
},
"human_customer_service": {
"score": 4,
"reason": "The speech sounds like a genuine human interaction with appropriate emotional cues."
}
},
"Y": {
"naturalness": {
"score": 3,
"reason": "The speech is somewhat robotic with unnatural pauses and intonation."
},
"expressive_fit": {
"score": 3,
"reason": "The speaker lacks emotional variation, making the message sound flat."
},
"thinking_behavior": {
"score": 3,
"reason": "The pause is unnatural and does not add to the thinking process."
},
"speaker_consistency": {
"score": 3,
"reason": "The speaker's tone and style are inconsistent, switching abruptly."
},
"human_customer_service": {
"score": 3,
"reason": "The speech sounds more like a machine-generated response than a human interaction."
}
},
"Z": {
"naturalness": {
"score": 5,
"reason": "The speech is very natural with smooth intonation and pacing."
},
"expressive_fit": {
"score": 5,
"reason": "The speaker effectively conveys happiness in confirmation and thoughtful consideration in checking the shipping time."
},
"thinking_behavior": {
"score": 5,
"reason": "The pause before checking the shipping time is natural and adds to the thinking process."
},
"speaker_consistency": {
"score": 5,
"reason": "The speaker maintains a consistent tone and style throughout the message."
},
"human_customer_service": {
"score": 5,
"reason": "The speech sounds like a genuine human interaction with appropriate emotional cues."
}
}
},
"ranking": [
"Z",
"X",
"Y"
],
"ranking_reason": "Clip Z has the most natural and expressive speech, followed by X, while Y has the least natural and expressive speech."
}
},
{
"alias_to_configuration": {
"X": "B_single_reference",
"Y": "C_24_reference_library",
"Z": "A_no_control_markers"
},
"response": {
"clips": {
"X": {
"naturalness": {
"score": 4,
"reason": "The speech is mostly natural, but the tone is slightly robotic."
},
"expressive_fit": {
"score": 4,
"reason": "The speaker conveys happiness and thoughtfulness, but the delivery is a bit monotonous."
},
"thinking_behavior": {
"score": 3,
"reason": "There is a slight pause, but it does not effectively convey thinking."
},
"speaker_consistency": {
"score": 4,
"reason": "The speaker maintains a consistent tone throughout."
},
"human_customer_service": {
"score": 4,
"reason": "The speech is clear and professional, but lacks some human-like nuances."
}
},
"Y": {
"naturalness": {
"score": 5,
"reason": "The speech is very natural and flows smoothly."
},
"expressive_fit": {
"score": 5,
"reason": "The speaker effectively conveys happiness and thoughtfulness with a natural pause."
},
"thinking_behavior": {
"score": 5,
"reason": "The pause is natural and effectively conveys thinking."
},
"speaker_consistency": {
"score": 5,
"reason": "The speaker maintains a consistent and natural tone throughout."
},
"human_customer_service": {
"score": 5,
"reason": "The speech is clear, professional, and has human-like nuances."
}
},
"Z": {
"naturalness": {
"score": 3,
"reason": "The speech is somewhat robotic and lacks natural flow."
},
"expressive_fit": {
"score": 3,
"reason": "The speaker conveys happiness and thoughtfulness, but the delivery is monotonous."
},
"thinking_behavior": {
"score": 2,
"reason": "There is no effective pause to convey thinking."
},
"speaker_consistency": {
"score": 3,
"reason": "The speaker maintains a consistent tone, but it is robotic."
},
"human_customer_service": {
"score": 3,
"reason": "The speech is clear but lacks human-like nuances."
}
}
},
"ranking": [
"Y",
"X",
"Z"
],
"ranking_reason": "Clip Y has the most natural flow, effective pauses, and human-like nuances, making it the best. Clip X is slightly robotic but maintains consistency. Clip Z is the least natural and lacks effective pauses."
}
},
{
"alias_to_configuration": {
"X": "C_24_reference_library",
"Y": "A_no_control_markers",
"Z": "B_single_reference"
},
"response": {
"clips": {
"X": {
"naturalness": {
"score": 4,
"reason": "The speech is mostly natural, but the pause before '让我查一下发货时间' is slightly abrupt."
},
"expressive_fit": {
"score": 4,
"reason": "The speaker conveys happiness and thoughtfulness well, but the transition between emotions could be smoother."
},
"thinking_behavior": {
"score": 3,
"reason": "The pause is present but feels a bit forced rather than natural."
},
"speaker_consistency": {
"score": 4,
"reason": "The speaker maintains a consistent tone throughout, but there is a slight variation in pace."
},
"human_customer_service": {
"score": 4,
"reason": "The speech sounds mostly human-like, but the pause is a bit robotic."
}
},
"Y": {
"naturalness": {
"score": 5,
"reason": "The speech flows naturally with no abrupt pauses or unnatural cadences."
},
"expressive_fit": {
"score": 5,
"reason": "The speaker effectively conveys happiness and thoughtfulness, with a smooth transition between emotions."
},
"thinking_behavior": {
"score": 5,
"reason": "The pause is natural and adds to the authenticity of the thinking process."
},
"speaker_consistency": {
"score": 5,
"reason": "The speaker maintains a consistent tone and pace throughout."
},
"human_customer_service": {
"score": 5,
"reason": "The speech sounds very human-like, with natural pauses and expressions."
}
},
"Z": {
"naturalness": {
"score": 3,
"reason": "The speech is somewhat robotic, with a lack of natural pauses and variations in tone."
},
"expressive_fit": {
"score": 3,
"reason": "The speaker conveys the emotions, but the delivery is flat and lacks natural expressiveness."
},
"thinking_behavior": {
"score": 2,
"reason": "There is no natural pause or thinking behavior, making the speech sound rushed."
},
"speaker_consistency": {
"score": 3,
"reason": "The speaker maintains a consistent tone, but it is monotonous and lacks variation."
},
"human_customer_service": {
"score": 3,
"reason": "The speech sounds somewhat robotic, with a lack of natural pauses and expressions."
}
}
},
"ranking": [
"Y",
"X",
"Z"
],
"ranking_reason": "Clip Y has the most natural flow, expressive fit, and human-like qualities. Clip X is close but has a slightly abrupt pause. Clip Z is the least natural and expressive."
}
}
],
"aggregate": {
"configurations": {
"A_no_control_markers": {
"dimension_means": {
"naturalness": 4.0,
"expressive_fit": 4.0,
"thinking_behavior": 3.6666666666666665,
"speaker_consistency": 4.0,
"human_customer_service": 4.0
},
"overall_mean": 3.9333333333333327,
"rank_points": 6
},
"B_single_reference": {
"dimension_means": {
"naturalness": 3.3333333333333335,
"expressive_fit": 3.3333333333333335,
"thinking_behavior": 2.6666666666666665,
"speaker_consistency": 3.3333333333333335,
"human_customer_service": 3.3333333333333335
},
"overall_mean": 3.2,
"rank_points": 4
},
"C_24_reference_library": {
"dimension_means": {
"naturalness": 4.666666666666667,
"expressive_fit": 4.666666666666667,
"thinking_behavior": 4.333333333333333,
"speaker_consistency": 4.666666666666667,
"human_customer_service": 4.666666666666667
},
"overall_mean": 4.6000000000000005,
"rank_points": 8
}
},
"aggregate_ranking": [
"C_24_reference_library",
"A_no_control_markers",
"B_single_reference"
],
"expected_manuscript_ranking": [
"C_24_reference_library",
"B_single_reference",
"A_no_control_markers"
],
"manuscript_quality_ordering_reproduced": false,
"near_human_customer_service_supported": true,
"manuscript_quality_claim_reproduced": false
},
"limitations": [
"This is a real multimodal-model listening study, not a human MOS panel.",
"Three position-balanced passes reduce order bias but share one judge model."
]
}
chapter6/controllable-tts/validation/latest.json
+117
View File
@@ -0,0 +1,117 @@
{
"experiment": "6-6",
"timestamp_utc": "2026-07-29T10:19:56.497167+00:00",
"provider": "Fish Audio",
"backend": "s1",
"reference_profile_count": 24,
"dimensions": {
"emotion": [
"neutral",
"happy",
"frustrated",
"thinking"
],
"speed": [
"normal",
"fast",
"slow"
],
"style": [
"formal",
"casual"
]
},
"input_with_markers": "[EMO:happy][SPEED:fast][STYLE:casual]太好了！您的订单已确认。[THINKING]让我查一下发货时间。[EMO:neutral][SPEED:normal][STYLE:formal]预计明天下午送达。",
"parse_trace": [
" [EMO:happy] -> 情绪 = happy",
" [SPEED:fast] -> 语速 = fast",
" [STYLE:casual] -> 风格 = casual",
" [THINKING] -> 切换到 思考/慢速/正式 参考语音",
" [THINKING] 停顿 -> 插入静音 1200ms",
" [THINKING] 填充音 -> Fish S1 原生标记 '(uncertain)嗯……' (情绪=thinking,语速=slow)",
" [EMO:neutral] -> 情绪 = neutral",
" [SPEED:normal] -> 语速 = normal",
" [STYLE:formal] -> 风格 = formal"
],
"outputs": {
"A_no_control_markers": {
"path": "/Users/boj/book/ai-agent-book/chapter6/controllable-tts/output/A_no_control_markers.mp3",
"probe": {
"duration": "5.355000",
"size": "85680"
}
},
"B_single_reference": {
"path": "/Users/boj/book/ai-agent-book/chapter6/controllable-tts/output/B_single_reference.mp3",
"segments": [
{
"model": "s1",
"provider": "Fish Audio",
"profile": "neutral_normal_formal",
"reference_path": "neutral_normal_formal.mp3",
"reference_sha256": "2cf4c64bb8222399ab54c63cc41049c572ea5f1b819ffdcbc496014daae004c0",
"fish_text": "太好了！您的订单已确认。让我查一下发货时间。预计明天下午送达。",
"type": "speech",
"text": "太好了！您的订单已确认。让我查一下发货时间。预计明天下午送达。"
}
],
"probe": {
"duration": "5.903563",
"size": "94457"
}
},
"C_24_reference_library": {
"path": "/Users/boj/book/ai-agent-book/chapter6/controllable-tts/output/C_24_reference_library.mp3",
"segments": [
{
"model": "s1",
"provider": "Fish Audio",
"profile": "happy_fast_casual",
"reference_path": "happy_fast_casual.mp3",
"reference_sha256": "0e96b8c6abe891c6292e6c7037aac67979ac407c3125301f5421afe35ce256d5",
"fish_text": "太好了！您的订单已确认。",
"type": "speech",
"text": "太好了！您的订单已确认。"
},
{
"type": "silence",
"ms": 1200
},
{
"model": "s1",
"provider": "Fish Audio",
"profile": "thinking_slow_formal",
"reference_path": "thinking_slow_formal.mp3",
"reference_sha256": "abef0a802382dad67b37e3447de08401a1d1cdb451420759853f4af9df234ac9",
"fish_text": "(uncertain)嗯……",
"type": "speech",
"text": "(uncertain)嗯……"
},
{
"model": "s1",
"provider": "Fish Audio",
"profile": "thinking_slow_formal",
"reference_path": "thinking_slow_formal.mp3",
"reference_sha256": "abef0a802382dad67b37e3447de08401a1d1cdb451420759853f4af9df234ac9",
"fish_text": "让我查一下发货时间。",
"type": "speech",
"text": "让我查一下发货时间。"
},
{
"model": "s1",
"provider": "Fish Audio",
"profile": "neutral_normal_formal",
"reference_path": "neutral_normal_formal.mp3",
"reference_sha256": "2cf4c64bb8222399ab54c63cc41049c572ea5f1b819ffdcbc496014daae004c0",
"fish_text": "预计明天下午送达。",
"type": "speech",
"text": "预计明天下午送达。"
}
],
"probe": {
"duration": "8.305306",
"size": "133790"
}
}
}
}