@polymorphism-tech/morph-spec 7.9.3 → 8.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (213) hide show
  1. package/CLAUDE.md +2 -2
  2. package/README.md +31 -2
  3. package/bin/morph-spec.js +50 -2
  4. package/bin/validate.js +379 -379
  5. package/claude-plugin.json +1 -1
  6. package/docs/CHEATSHEET.md +38 -1
  7. package/docs/QUICKSTART.md +60 -1
  8. package/framework/CLAUDE.md +13 -2
  9. package/framework/MORPH.md +38 -2
  10. package/framework/agents.json +22 -3
  11. package/framework/commands/commit.md +166 -166
  12. package/framework/commands/morph-hotfix.md +39 -0
  13. package/framework/commands/morph-infra.md +215 -215
  14. package/framework/commands/morph-preflight.md +205 -205
  15. package/framework/commands/morph-troubleshoot.md +124 -124
  16. package/framework/hooks/README.md +25 -10
  17. package/framework/hooks/claude-code/core/gate-guard.js +4 -2
  18. package/framework/hooks/claude-code/core/loop-detect.js +2 -1
  19. package/framework/hooks/claude-code/core/post-edit-typecheck.js +14 -5
  20. package/framework/hooks/claude-code/core/tasks-json-guard.js +4 -2
  21. package/framework/hooks/claude-code/core/validate-completion.js +1 -1
  22. package/framework/hooks/claude-code/core/worktree-context.js +160 -0
  23. package/framework/hooks/claude-code/statusline.py +679 -679
  24. package/framework/hooks/claude-code/statusline.sh +11 -11
  25. package/framework/hooks/git/commit-msg/conventional-commits.sh +33 -33
  26. package/framework/hooks/git/pre-commit/agents.sh +25 -25
  27. package/framework/hooks/git/pre-commit/orchestrator.sh +64 -64
  28. package/framework/hooks/git/pre-commit/specs.sh +50 -50
  29. package/framework/hooks/git/pre-push/run-tests.sh +44 -44
  30. package/framework/hooks/shared/activity-logger.js +160 -160
  31. package/framework/hooks/shared/build-check.js +2 -2
  32. package/framework/hooks/shared/hook-response.js +17 -5
  33. package/framework/hooks/shared/payload-utils.js +42 -0
  34. package/framework/hooks/shared/state-reader.js +22 -2
  35. package/framework/hooks/shared/stdin-reader.js +26 -26
  36. package/framework/rubrics/backend.json +41 -41
  37. package/framework/rules/ai-agents-standards.md +45 -45
  38. package/framework/rules/dotnet-templates.md +86 -86
  39. package/framework/rules/frontend-standards.md +13 -13
  40. package/framework/rules/infrastructure-standards.md +27 -27
  41. package/framework/rules/neon-standards.md +25 -25
  42. package/framework/rules/nextjs-standards.md +20 -20
  43. package/framework/rules/nextjs-templates.md +40 -40
  44. package/framework/schemas/feature.schema.json +95 -1
  45. package/framework/skills/core/create-umbraco-lp/SKILL.md +1 -1
  46. package/framework/skills/core/migrate-lp-to-umbraco/SKILL.md +1 -1
  47. package/framework/skills/core/morph-apply/SKILL.md +39 -8
  48. package/framework/skills/core/morph-brainstorming/SKILL.md +9 -1
  49. package/framework/skills/core/morph-eval/SKILL.md +6 -1
  50. package/framework/skills/core/morph-hotfix/SKILL.md +136 -0
  51. package/framework/skills/core/morph-implement/SKILL.md +8 -4
  52. package/framework/skills/core/morph-plan/SKILL.md +5 -1
  53. package/framework/skills/core/morph-proposal/SKILL.md +24 -1
  54. package/framework/skills/core/morph-review/SKILL.md +3 -2
  55. package/framework/skills/core/morph-stack-scan/SKILL.md +1 -1
  56. package/framework/skills/core/morph-standards/SKILL.md +1 -1
  57. package/framework/standards/STANDARDS.json +7 -2
  58. package/framework/standards/ai-agents/agent-session.md +160 -160
  59. package/framework/standards/ai-agents/batching.md +193 -193
  60. package/framework/standards/ai-agents/context-providers.md +188 -188
  61. package/framework/standards/ai-agents/mcp-server.md +250 -250
  62. package/framework/standards/ai-agents/mcp-tools.md +197 -197
  63. package/framework/standards/ai-agents/middleware-patterns.md +207 -207
  64. package/framework/standards/ai-agents/modalities-image-gen.md +173 -173
  65. package/framework/standards/ai-agents/modalities-speech-to-text.md +171 -171
  66. package/framework/standards/ai-agents/modalities-text-to-speech.md +181 -181
  67. package/framework/standards/ai-agents/modalities-vision.md +201 -201
  68. package/framework/standards/ai-agents/multi-agent-patterns.md +155 -155
  69. package/framework/standards/ai-agents/production.md +275 -275
  70. package/framework/standards/ai-agents/prompts-in-db.md +214 -214
  71. package/framework/standards/ai-agents/providers/model-registry.md +158 -158
  72. package/framework/standards/ai-agents/service-tier-flex.md +135 -135
  73. package/framework/standards/ai-agents/structured-output.md +249 -249
  74. package/framework/standards/ai-agents/sweet-spot.md +109 -109
  75. package/framework/standards/backend/integrations/neon-auth/neon-auth.md +45 -3
  76. package/framework/templates/.idea/morph-templates.xml +92 -0
  77. package/framework/templates/.vscode/morph-templates.code-snippets +186 -0
  78. package/framework/templates/IDE-SNIPPETS.md +262 -262
  79. package/framework/templates/REGISTRY.json +0 -62
  80. package/framework/templates/code/dotnet/abstractions/api-endpoint.cs +7 -7
  81. package/framework/templates/code/dotnet/ai-agents/AgentBootstrap.cs.template +39 -39
  82. package/framework/templates/code/dotnet/ai-agents/EmbeddingService.cs.template +68 -68
  83. package/framework/templates/code/dotnet/ai-agents/ModelRegistry.cs.template +117 -117
  84. package/framework/templates/code/dotnet/ai-agents/PromptRepository.cs.template +95 -95
  85. package/framework/templates/code/dotnet/ai-agents/ResilientToolMiddleware.cs.template +61 -61
  86. package/framework/templates/code/dotnet/ai-agents/VectorSearchTool.cs.template +107 -107
  87. package/framework/templates/code/dotnet/ai-agents/model-registry.json.template +58 -58
  88. package/framework/templates/code/dotnet/contracts/contracts-vsa.cs +281 -281
  89. package/framework/templates/code/dotnet/database/migration.cs +83 -83
  90. package/framework/templates/code/dotnet/feature/endpoint.cs.hbs +21 -21
  91. package/framework/templates/code/dotnet/feature/request.cs.hbs +4 -4
  92. package/framework/templates/code/dotnet/feature/response.cs.hbs +4 -4
  93. package/framework/templates/code/dotnet/feature/validator.cs.hbs +15 -15
  94. package/framework/templates/code/sql/ai-agents/agent-prompts-migration.sql.template +58 -58
  95. package/framework/templates/code/sql/ai-agents/pgvector-embeddings-migration.sql.template +91 -91
  96. package/framework/templates/code/typescript/contracts.ts +167 -167
  97. package/framework/templates/docs/clarifications.md +253 -253
  98. package/framework/templates/docs/schema-analysis.md +119 -119
  99. package/framework/templates/docs/ui-components.md +52 -52
  100. package/framework/templates/docs/ui-design-system.md +76 -76
  101. package/framework/templates/docs/ui-flows.md +167 -167
  102. package/framework/templates/docs/ui-mockups.md +98 -98
  103. package/framework/templates/feature/decisions.md +122 -122
  104. package/framework/templates/frontend/nextjs/Dockerfile.nextjs.hbs +43 -43
  105. package/framework/templates/frontend/nextjs/client-component.tsx.hbs +26 -26
  106. package/framework/templates/frontend/nextjs/env.mjs.hbs +32 -32
  107. package/framework/templates/frontend/nextjs/feature-form.tsx.hbs +56 -56
  108. package/framework/templates/frontend/nextjs/page.tsx.hbs +22 -22
  109. package/framework/templates/frontend/nextjs/tsconfig.json.hbs +26 -26
  110. package/framework/templates/frontend/nextjs/use-feature.ts.hbs +54 -54
  111. package/framework/templates/infrastructure/docker/Dockerfile.template +58 -58
  112. package/framework/templates/infrastructure/docker/docker-compose.template.yml +50 -50
  113. package/framework/templates/infrastructure/docker/dockerfile-api.dockerfile +38 -38
  114. package/framework/templates/infrastructure/docker/dockerfile-web.dockerfile +48 -48
  115. package/framework/templates/infrastructure/github/README.md +56 -56
  116. package/framework/templates/infrastructure/github/actions/docker-build-push/action.yml.hbs +45 -45
  117. package/framework/templates/infrastructure/github/actions/health-check/action.yml.hbs +27 -27
  118. package/framework/templates/infrastructure/github/workflows/docker-build-push.yml.hbs +59 -59
  119. package/framework/templates/infrastructure/github/workflows/dotnet-build.yml.hbs +39 -39
  120. package/framework/templates/integrations/asaas-client.cs +387 -387
  121. package/framework/templates/integrations/asaas-webhook.cs +351 -351
  122. package/framework/templates/meta-prompts/fusion/fusion-agent.md +76 -76
  123. package/framework/templates/meta-prompts/fusion/fusion-aggregator.md +100 -100
  124. package/framework/templates/meta-prompts/validators/pre-commit-validator.md +95 -95
  125. package/framework/templates/project/validate.js +120 -120
  126. package/framework/templates/state.template.json +17 -17
  127. package/framework/templates/ui/design-system.css +226 -226
  128. package/package.json +1 -1
  129. package/src/commands/dashboard/dashboard.js +53 -53
  130. package/src/commands/index.js +13 -13
  131. package/src/commands/mcp/mcp-setup.js +519 -519
  132. package/src/commands/project/checkpoint.js +209 -209
  133. package/src/commands/project/doctor.js +4 -2
  134. package/src/commands/project/init.js +46 -2
  135. package/src/commands/project/update.js +5 -3
  136. package/src/commands/project/worktree.js +1005 -46
  137. package/src/commands/state/advance.js +17 -2
  138. package/src/commands/state/approve.js +18 -1
  139. package/src/commands/state/create.js +158 -14
  140. package/src/commands/state/retype.js +126 -0
  141. package/src/commands/state/score.js +4 -0
  142. package/src/commands/tasks/dag.js +32 -0
  143. package/src/commands/validation/index.js +1 -0
  144. package/src/commands/validation/validate-feature.js +33 -5
  145. package/src/commands/validation/verify.js +190 -0
  146. package/src/core/state/phase-state-machine.js +197 -197
  147. package/src/core/state/state-manager.js +35 -10
  148. package/src/core/templates/template-renderer.js +477 -477
  149. package/src/core/work-types.js +79 -0
  150. package/src/dashboard/app/components/DetailPanel.jsx +11 -11
  151. package/src/dashboard/app/components/FlowGraph.jsx +17 -17
  152. package/src/dashboard/app/components/SearchFilter.jsx +22 -22
  153. package/src/dashboard/app/hooks/useDetailPanel.js +15 -15
  154. package/src/dashboard/app/main.jsx +13 -13
  155. package/src/dashboard/app/pages/AgentMap.jsx +370 -370
  156. package/src/dashboard/app/pages/HookInspector.jsx +418 -418
  157. package/src/dashboard/app/pages/LiveState.jsx +11 -1
  158. package/src/dashboard/app/pages/PhasePipeline.jsx +408 -408
  159. package/src/dashboard/app/pages/RulesMap.jsx +273 -273
  160. package/src/dashboard/app/pages/SkillsLibrary.jsx +366 -366
  161. package/src/dashboard/app/pages/Standards.jsx +332 -332
  162. package/src/dashboard/app/styles/index.css +47 -47
  163. package/src/dashboard/index.html +12 -12
  164. package/src/dashboard/package.json +24 -24
  165. package/src/dashboard/scanner/hooks-scanner.js +41 -41
  166. package/src/dashboard/scanner/phases-scanner.js +15 -15
  167. package/src/dashboard/scanner/rubrics-scanner.js +12 -12
  168. package/src/dashboard/scanner/rules-scanner.js +37 -37
  169. package/src/dashboard/scanner/skills-scanner.js +43 -43
  170. package/src/dashboard/scanner/squads-scanner.js +13 -13
  171. package/src/dashboard/scanner/standards-scanner.js +26 -26
  172. package/src/dashboard/scanner/state-scanner.js +42 -0
  173. package/src/dashboard/vite-plugin-morph-data.js +17 -17
  174. package/src/dashboard/vite.config.js +24 -24
  175. package/src/lib/agents/metrics-aggregator.js +56 -56
  176. package/src/lib/agents/metrics-calculator.js +125 -125
  177. package/src/lib/agents/output-collector.js +73 -73
  178. package/src/lib/detectors/claude-config-detector.js +152 -152
  179. package/src/lib/detectors/design-system-detector.js +231 -231
  180. package/src/lib/detectors/index.js +217 -217
  181. package/src/lib/generators/architecture-scanner.js +639 -639
  182. package/src/lib/generators/design-system-generator.js +508 -508
  183. package/src/lib/generators/index.js +13 -13
  184. package/src/lib/generators/settings-generator.js +209 -209
  185. package/src/lib/hooks/hook-executor.js +167 -167
  186. package/src/lib/installers/mcp-installer.js +719 -719
  187. package/src/lib/installers/memory-installer.js +1 -1
  188. package/src/lib/risk-detector.js +16 -0
  189. package/src/lib/tasks/dispatch-planner.js +122 -4
  190. package/src/lib/tasks/mermaid-renderer.js +132 -0
  191. package/src/lib/tasks/task-classifier.js +30 -30
  192. package/src/lib/tasks/task-parser.js +209 -209
  193. package/src/lib/tasks/test-runner.js +27 -6
  194. package/src/lib/validators/architecture/architecture-validator.js +259 -259
  195. package/src/lib/validators/checkpoint-persistence.js +39 -39
  196. package/src/lib/validators/contracts/contract-compliance-validator.js +274 -274
  197. package/src/lib/validators/css/css-validator.js +340 -340
  198. package/src/lib/validators/packages/package-validator.js +347 -347
  199. package/src/lib/validators/shared/emit-validator-dispatch.js +14 -14
  200. package/src/lib/validators/shared/issue-counter.js +14 -14
  201. package/src/lib/validators/validation-runner.js +349 -349
  202. package/src/lib/validators/verify-runner.js +322 -0
  203. package/src/lib/work-type-detector.js +143 -0
  204. package/src/scripts/setup-infra.js +32 -5
  205. package/src/utils/agent-id-mapper.js +11 -11
  206. package/src/utils/agents-installer.js +10 -6
  207. package/src/utils/claude-settings-manager.js +300 -300
  208. package/src/utils/file-copier.js +43 -0
  209. package/src/utils/hooks-installer.js +41 -11
  210. package/src/utils/skills-installer.js +174 -174
  211. package/framework/templates/meta-prompts/parallel-workers/parallel-coordinator.md +0 -113
  212. package/framework/templates/meta-prompts/parallel-workers/parallel-worker.md +0 -80
  213. package/src/lib/tasks/wave-resolver.js +0 -353
@@ -1,181 +1,181 @@
1
- # Modalities — Text to Speech (Text to Audio)
2
-
3
- > **Scope:** stacks=["dotnet"]
4
- > **Layer:** 2 (on-keyword)
5
- > **Keywords:** text to speech, TTS, voice synthesis, audio generation, speech synthesis
6
- > **Read by Claude in:** implement (quando o projeto precisa gerar áudio a partir de texto)
7
-
8
- **Verified against:** MAF 1.0 GA + OpenAI .NET SDK 2.x. Last-verified: 2026-05-19.
9
-
10
- ---
11
-
12
- ## Quando usar TTS
13
-
14
- TTS converte texto em áudio narrado. É um caso de uso **raro** — só adicione quando há demanda real e comprovada:
15
-
16
- - **Acessibilidade:** leitura em voz alta para usuários com deficiência visual ou dificuldade de leitura
17
- - **Notificações em áudio:** resumos falados de alertas ou relatórios em contextos hands-free (painel industrial, carro)
18
- - **Resumos falados:** o usuário quer ouvir um digest em vez de ler (ex: podcast personalizado gerado on-demand)
19
-
20
- **Nota honesta:** TTS tem custo por caractere e latência perceptível. Se o caso de uso não é explicitamente solicitado pelo usuário final ou pelo cliente, não adicione — um botão "copiar texto" ou um leitor de tela nativo do SO resolve a maioria dos casos de acessibilidade sem custo de API.
21
-
22
- TTS é uma **chamada de serviço**, não um agente conversacional. Use `AudioClient` diretamente via DI — não crie `AIAgent` para isso.
23
-
24
- ---
25
-
26
- ## A API
27
-
28
- No OpenAI SDK (.NET 2.x), o caminho é `AudioClient.GenerateSpeech`:
29
-
30
- ```csharp
31
- using OpenAI.Audio;
32
-
33
- AudioClient client = new("tts-1", apiKey);
34
- BinaryData speech = await client.GenerateSpeechAsync(text, GeneratedSpeechVoice.Alloy);
35
- ```
36
-
37
- Retorna `BinaryData` (bytes de áudio) que você persiste ou serve via stream. Para controlar formato e velocidade, use `SpeechGenerationOptions`.
38
-
39
- ---
40
-
41
- ## Exemplo C# completo
42
-
43
- ```csharp
44
- using OpenAI.Audio;
45
- using Microsoft.Extensions.Configuration;
46
-
47
- public sealed class TextToSpeechService
48
- {
49
- private readonly AudioClient _client;
50
-
51
- public TextToSpeechService(IConfiguration config)
52
- {
53
- // tts-1: mais rápido, menor qualidade. tts-1-hd: mais lento, maior qualidade.
54
- var model = config["TTS:Model"] ?? "tts-1";
55
- var apiKey = config["OpenAI:ApiKey"]!;
56
- _client = new AudioClient(model, apiKey);
57
- }
58
-
59
- /// <summary>
60
- /// Converte texto em áudio e retorna bytes MP3.
61
- /// Cachear o resultado é altamente recomendado para textos repetitivos — gerar o mesmo texto
62
- /// duas vezes é desperdício de custo e latência.
63
- /// </summary>
64
- public async Task<BinaryData> SynthesizeAsync(
65
- string text,
66
- GeneratedSpeechVoice? voice = null,
67
- GeneratedSpeechFormat? format = null,
68
- float speedRatio = 1.0f,
69
- CancellationToken ct = default)
70
- {
71
- var resolvedVoice = voice ?? GeneratedSpeechVoice.Alloy;
72
- var resolvedFormat = format ?? GeneratedSpeechFormat.Mp3;
73
-
74
- var options = new SpeechGenerationOptions
75
- {
76
- ResponseFormat = resolvedFormat,
77
- SpeedRatio = speedRatio
78
- };
79
-
80
- BinaryData speech = await _client.GenerateSpeechAsync(text, resolvedVoice, options, ct);
81
- return speech;
82
- }
83
- }
84
- ```
85
-
86
- **Registro DI:**
87
-
88
- ```csharp
89
- // Program.cs
90
- builder.Services.AddSingleton<TextToSpeechService>();
91
- ```
92
-
93
- **Servindo como download ou stream:**
94
-
95
- ```csharp
96
- public class AudioController(TextToSpeechService tts) : ControllerBase
97
- {
98
- [HttpPost("synthesize")]
99
- public async Task<IActionResult> Synthesize([FromBody] SynthesizeRequest req)
100
- {
101
- // Verificar cache antes de gerar (ver Anti-patterns)
102
- BinaryData audio = await tts.SynthesizeAsync(
103
- text: req.Text,
104
- voice: GeneratedSpeechVoice.Nova,
105
- format: GeneratedSpeechFormat.Mp3,
106
- speedRatio: 1.1f);
107
-
108
- // the storage layer may assign the final name; use a timestamp-based name here
109
- var fileName = $"tts-{DateTime.UtcNow:yyyyMMddHHmmss}.mp3";
110
- return File(audio.ToStream(), "audio/mpeg", fileName);
111
- }
112
- }
113
- ```
114
-
115
- ---
116
-
117
- ## Parâmetros
118
-
119
- > Valores verificados contra OpenAI TTS API + OpenAI .NET SDK 2.x (2026-05-19).
120
-
121
- **Vozes disponíveis (`GeneratedSpeechVoice`):**
122
-
123
- | Voz | Característica |
124
- |-----|---------------|
125
- | `Alloy` | Neutra, versátil — boa escolha padrão |
126
- | `Echo` | Masculina, suave |
127
- | `Fable` | Britânica, expressiva |
128
- | `Onyx` | Masculina, grave |
129
- | `Nova` | Feminina, amigável |
130
- | `Shimmer` | Feminina, suave |
131
-
132
- **Formatos de saída (`GeneratedSpeechFormat`):**
133
-
134
- | Formato | Caso de uso |
135
- |---------|-------------|
136
- | `Mp3` | Default — compatibilidade universal |
137
- | `Opus` | Streaming de baixa latência |
138
- | `Aac` | Dispositivos Apple / YouTube |
139
- | `Flac` | Arquivo sem perda |
140
- | `Wav` | Processamento de áudio downstream |
141
- | `Pcm` | Raw bytes sem container |
142
-
143
- **`SpeedRatio`:** `0.25` (muito lento) a `4.0` (muito rápido). Padrão `1.0`.
144
-
145
- **Modelos:**
146
- - `tts-1` — rápido, custo menor, qualidade suficiente para a maioria dos casos
147
- - `tts-1-hd` — maior qualidade, mais lento e mais caro — use apenas quando a clareza de voz é crítica
148
-
149
- ---
150
-
151
- ## Anti-patterns
152
-
153
- | Anti-pattern | Por quê é errado | Jeito certo |
154
- |--------------|-----------------|-------------|
155
- | Adicionar TTS sem caso de uso real | Custo por caractere + latência sem benefício ao usuário | Só adicione com demanda explícita; leitores de tela nativos cobrem acessibilidade básica |
156
- | Gerar o mesmo texto repetidamente sem cache | Textos fixos (intro, disclaimers, respostas FAQ) custam o mesmo toda vez | Cachear bytes de áudio para textos invariantes — CDN ou Redis com key baseada em hash do texto + voz + formato |
157
- | Criar `AIAgent` para TTS | `AudioClient.GenerateSpeech` não é conversacional; não há raciocínio LLM envolvido | Injete `TextToSpeechService` via DI — é um serviço de síntese, não um agente |
158
- | Gerar texto longo de uma vez sem segmentar | Providers têm limite de caracteres por request (OpenAI: ~4096 tokens / ~4000 chars); textos muito longos falham | Divida em parágrafos, gere áudio por segmento, concatene os bytes |
159
-
160
- ---
161
-
162
- ## Checklist (verifiable by morph-eval)
163
-
164
- - [ ] `AudioClient` injetado via DI — não instanciado inline
165
- - [ ] Cache implementado para textos invariantes (não gera o mesmo áudio duas vezes)
166
- - [ ] Textos longos segmentados antes de enviar ao provider
167
- - [ ] `GeneratedSpeechVoice` e `GeneratedSpeechFormat` escolhidos adequados ao contexto (não só defaults)
168
- - [ ] Model e API key vêm de config, não hardcoded
169
- - [ ] Não usa `AIAgent`/`AsAIAgent` para TTS — é um `TextToSpeechService`
170
-
171
- ---
172
-
173
- ## References
174
-
175
- - `ai-agents-setup` — packages, DI, e providers disponíveis
176
- - `ai-agents-providers-model-registry` — padrão de alias; adapte para resolver `AudioClient` por provider
177
- - OpenAI .NET SDK — `AudioClient`: https://github.com/openai/openai-dotnet
178
-
179
- ---
180
-
181
- *MORPH-SPEC by Polymorphism Tech — ai-agents/modalities-text-to-speech.md v1.0 (2026-05-19)*
1
+ # Modalities — Text to Speech (Text to Audio)
2
+
3
+ > **Scope:** stacks=["dotnet"]
4
+ > **Layer:** 2 (on-keyword)
5
+ > **Keywords:** text to speech, TTS, voice synthesis, audio generation, speech synthesis
6
+ > **Read by Claude in:** implement (quando o projeto precisa gerar áudio a partir de texto)
7
+
8
+ **Verified against:** MAF 1.0 GA + OpenAI .NET SDK 2.x. Last-verified: 2026-05-19.
9
+
10
+ ---
11
+
12
+ ## Quando usar TTS
13
+
14
+ TTS converte texto em áudio narrado. É um caso de uso **raro** — só adicione quando há demanda real e comprovada:
15
+
16
+ - **Acessibilidade:** leitura em voz alta para usuários com deficiência visual ou dificuldade de leitura
17
+ - **Notificações em áudio:** resumos falados de alertas ou relatórios em contextos hands-free (painel industrial, carro)
18
+ - **Resumos falados:** o usuário quer ouvir um digest em vez de ler (ex: podcast personalizado gerado on-demand)
19
+
20
+ **Nota honesta:** TTS tem custo por caractere e latência perceptível. Se o caso de uso não é explicitamente solicitado pelo usuário final ou pelo cliente, não adicione — um botão "copiar texto" ou um leitor de tela nativo do SO resolve a maioria dos casos de acessibilidade sem custo de API.
21
+
22
+ TTS é uma **chamada de serviço**, não um agente conversacional. Use `AudioClient` diretamente via DI — não crie `AIAgent` para isso.
23
+
24
+ ---
25
+
26
+ ## A API
27
+
28
+ No OpenAI SDK (.NET 2.x), o caminho é `AudioClient.GenerateSpeech`:
29
+
30
+ ```csharp
31
+ using OpenAI.Audio;
32
+
33
+ AudioClient client = new("tts-1", apiKey);
34
+ BinaryData speech = await client.GenerateSpeechAsync(text, GeneratedSpeechVoice.Alloy);
35
+ ```
36
+
37
+ Retorna `BinaryData` (bytes de áudio) que você persiste ou serve via stream. Para controlar formato e velocidade, use `SpeechGenerationOptions`.
38
+
39
+ ---
40
+
41
+ ## Exemplo C# completo
42
+
43
+ ```csharp
44
+ using OpenAI.Audio;
45
+ using Microsoft.Extensions.Configuration;
46
+
47
+ public sealed class TextToSpeechService
48
+ {
49
+ private readonly AudioClient _client;
50
+
51
+ public TextToSpeechService(IConfiguration config)
52
+ {
53
+ // tts-1: mais rápido, menor qualidade. tts-1-hd: mais lento, maior qualidade.
54
+ var model = config["TTS:Model"] ?? "tts-1";
55
+ var apiKey = config["OpenAI:ApiKey"]!;
56
+ _client = new AudioClient(model, apiKey);
57
+ }
58
+
59
+ /// <summary>
60
+ /// Converte texto em áudio e retorna bytes MP3.
61
+ /// Cachear o resultado é altamente recomendado para textos repetitivos — gerar o mesmo texto
62
+ /// duas vezes é desperdício de custo e latência.
63
+ /// </summary>
64
+ public async Task<BinaryData> SynthesizeAsync(
65
+ string text,
66
+ GeneratedSpeechVoice? voice = null,
67
+ GeneratedSpeechFormat? format = null,
68
+ float speedRatio = 1.0f,
69
+ CancellationToken ct = default)
70
+ {
71
+ var resolvedVoice = voice ?? GeneratedSpeechVoice.Alloy;
72
+ var resolvedFormat = format ?? GeneratedSpeechFormat.Mp3;
73
+
74
+ var options = new SpeechGenerationOptions
75
+ {
76
+ ResponseFormat = resolvedFormat,
77
+ SpeedRatio = speedRatio
78
+ };
79
+
80
+ BinaryData speech = await _client.GenerateSpeechAsync(text, resolvedVoice, options, ct);
81
+ return speech;
82
+ }
83
+ }
84
+ ```
85
+
86
+ **Registro DI:**
87
+
88
+ ```csharp
89
+ // Program.cs
90
+ builder.Services.AddSingleton<TextToSpeechService>();
91
+ ```
92
+
93
+ **Servindo como download ou stream:**
94
+
95
+ ```csharp
96
+ public class AudioController(TextToSpeechService tts) : ControllerBase
97
+ {
98
+ [HttpPost("synthesize")]
99
+ public async Task<IActionResult> Synthesize([FromBody] SynthesizeRequest req)
100
+ {
101
+ // Verificar cache antes de gerar (ver Anti-patterns)
102
+ BinaryData audio = await tts.SynthesizeAsync(
103
+ text: req.Text,
104
+ voice: GeneratedSpeechVoice.Nova,
105
+ format: GeneratedSpeechFormat.Mp3,
106
+ speedRatio: 1.1f);
107
+
108
+ // the storage layer may assign the final name; use a timestamp-based name here
109
+ var fileName = $"tts-{DateTime.UtcNow:yyyyMMddHHmmss}.mp3";
110
+ return File(audio.ToStream(), "audio/mpeg", fileName);
111
+ }
112
+ }
113
+ ```
114
+
115
+ ---
116
+
117
+ ## Parâmetros
118
+
119
+ > Valores verificados contra OpenAI TTS API + OpenAI .NET SDK 2.x (2026-05-19).
120
+
121
+ **Vozes disponíveis (`GeneratedSpeechVoice`):**
122
+
123
+ | Voz | Característica |
124
+ |-----|---------------|
125
+ | `Alloy` | Neutra, versátil — boa escolha padrão |
126
+ | `Echo` | Masculina, suave |
127
+ | `Fable` | Britânica, expressiva |
128
+ | `Onyx` | Masculina, grave |
129
+ | `Nova` | Feminina, amigável |
130
+ | `Shimmer` | Feminina, suave |
131
+
132
+ **Formatos de saída (`GeneratedSpeechFormat`):**
133
+
134
+ | Formato | Caso de uso |
135
+ |---------|-------------|
136
+ | `Mp3` | Default — compatibilidade universal |
137
+ | `Opus` | Streaming de baixa latência |
138
+ | `Aac` | Dispositivos Apple / YouTube |
139
+ | `Flac` | Arquivo sem perda |
140
+ | `Wav` | Processamento de áudio downstream |
141
+ | `Pcm` | Raw bytes sem container |
142
+
143
+ **`SpeedRatio`:** `0.25` (muito lento) a `4.0` (muito rápido). Padrão `1.0`.
144
+
145
+ **Modelos:**
146
+ - `tts-1` — rápido, custo menor, qualidade suficiente para a maioria dos casos
147
+ - `tts-1-hd` — maior qualidade, mais lento e mais caro — use apenas quando a clareza de voz é crítica
148
+
149
+ ---
150
+
151
+ ## Anti-patterns
152
+
153
+ | Anti-pattern | Por quê é errado | Jeito certo |
154
+ |--------------|-----------------|-------------|
155
+ | Adicionar TTS sem caso de uso real | Custo por caractere + latência sem benefício ao usuário | Só adicione com demanda explícita; leitores de tela nativos cobrem acessibilidade básica |
156
+ | Gerar o mesmo texto repetidamente sem cache | Textos fixos (intro, disclaimers, respostas FAQ) custam o mesmo toda vez | Cachear bytes de áudio para textos invariantes — CDN ou Redis com key baseada em hash do texto + voz + formato |
157
+ | Criar `AIAgent` para TTS | `AudioClient.GenerateSpeech` não é conversacional; não há raciocínio LLM envolvido | Injete `TextToSpeechService` via DI — é um serviço de síntese, não um agente |
158
+ | Gerar texto longo de uma vez sem segmentar | Providers têm limite de caracteres por request (OpenAI: ~4096 tokens / ~4000 chars); textos muito longos falham | Divida em parágrafos, gere áudio por segmento, concatene os bytes |
159
+
160
+ ---
161
+
162
+ ## Checklist (verifiable by morph-eval)
163
+
164
+ - [ ] `AudioClient` injetado via DI — não instanciado inline
165
+ - [ ] Cache implementado para textos invariantes (não gera o mesmo áudio duas vezes)
166
+ - [ ] Textos longos segmentados antes de enviar ao provider
167
+ - [ ] `GeneratedSpeechVoice` e `GeneratedSpeechFormat` escolhidos adequados ao contexto (não só defaults)
168
+ - [ ] Model e API key vêm de config, não hardcoded
169
+ - [ ] Não usa `AIAgent`/`AsAIAgent` para TTS — é um `TextToSpeechService`
170
+
171
+ ---
172
+
173
+ ## References
174
+
175
+ - `ai-agents-setup` — packages, DI, e providers disponíveis
176
+ - `ai-agents-providers-model-registry` — padrão de alias; adapte para resolver `AudioClient` por provider
177
+ - OpenAI .NET SDK — `AudioClient`: https://github.com/openai/openai-dotnet
178
+
179
+ ---
180
+
181
+ *MORPH-SPEC by Polymorphism Tech — ai-agents/modalities-text-to-speech.md v1.0 (2026-05-19)*