Give read-aloud a Portuguese voice, and a slower one

Phase 21's infra half. Two things the pt-PT pair needs from TTS, and one thing every learner has wanted since Phase 11. **A language is no longer a code change.** The handler knew exactly two languages, named in the Config struct: English on TTS_ENDPOINT and Chinese on TTS_ENDPOINT_ZH. Petal now discovers its Piper instances from the environment — English keeps the unsuffixed pair it has always had, and every other language is a TTS_ENDPOINT_<LANG>/TTS_VOICE_<LANG> pair — so fr and es cost a compose service and two lines of .env. <LANG> is the base tag, because an environment variable name cannot hold pt-PT's hyphen and only one Portuguese model is loaded either way. A language configured by halves is dropped rather than routed: half a configuration should reach the client as "no voice here, use Web Speech", not as an instance that errors on every tap. The startup line now names the voices it actually resolved rather than the English endpoint it was handed — the same lesson the dictionary line learned last week. **pt_PT-tugão-medium is the only European voice Piper ships.** The other five pt models in the catalogue are Brazilian, so the default anyone reaches for is the wrong country — the same trap as `dictionary-pt` packaging VERO, arriving through the catalogue rather than through the model. Named explicitly in compose, with the query that checks it in the deploy README. **The slow replay** (SUGGESTIONS §5e) is `slow: true` on /api/tts, raising Piper's length_scale to ~4/3. Piper stretches durations rather than resampling, so it stays a voice instead of a groan. The pace is part of the cache key — without it the slow replay of a word already heard at normal speed would be served back at normal speed, which is the one request where the difference is the whole point. 🐢 sits beside 🔊 on the word card, the selection bubble and the garden flashcard; the Web Speech fallback slows too, so the button means the same thing when Piper is down. **And the other reading gets her own voice.** The `alsoIn` block — the Portuguese sense of a word that is also English — now speaks in the pair's locale, which the pack names (`locale`) rather than anything inferring it from the letters. "comum" is spelled identically in both halves; a detector would have to guess, and this is the same reason the gloss shows both directions instead of picking one. Tests: config discovery (both existing deployment shapes, half-configured languages dropped, the pre-map voice defaults preserved), the slow scale and its separate cache entry, pt routing on the base tag with pt-BR landing on the European instance, and speech.ts's request body. The i18n shape suite now asserts every pack names a speakable locale in its own language — and that pt-PT's is not pt-BR. Verified: go build/vet/test, tsc, vitest 125/125, vite build. Live smoke against two fake Piper servers: en/pt × normal/slow all reached the right instance at the right length_scale with four distinct cache entries, and an unconfigured language still 404s.
2026-07-27 13:21:45 -07:00
parent ccb43e5a4d
commit 24c3533e18
18 changed files with 595 additions and 66 deletions
@@ -2,6 +2,7 @@ package config

 import (
 	"os"
+	"strings"
 	"time"
 )

@@ -29,10 +30,16 @@ type Config struct {
 	// TTS (read-aloud). Off unless TTSEndpoint is set — when empty, the /api/tts
 	// route isn't mounted and the frontend falls back to the browser's Web Speech
 	// API. Endpoint points at a local Piper HTTP server.
-	TTSEndpoint   string // Piper instance serving the English voice
-	TTSEndpointZH string // Piper instance serving the Chinese voice; empty = zh falls back to Web Speech
-	TTSVoiceEN    string // Piper voice id for English (e.g. en_US-amy-medium)
-	TTSVoiceZH    string // Piper voice id for Chinese (e.g. zh_CN-huayan-medium)
+	TTSEndpoint string // Piper instance serving the English voice; also the on/off switch
+	// TTSVoices is every language Petal can read aloud, keyed by base language
+	// tag ("en", "zh", "pt", …). Each Piper server loads exactly one model, so
+	// a language *is* an instance — and the instances are discovered from the
+	// environment rather than named in this struct: one
+	// TTS_ENDPOINT_<LANG>/TTS_VOICE_<LANG> pair per language, so the fr and es
+	// pairs cost a compose service and two lines of .env rather than a code
+	// change. English keeps the unsuffixed TTS_ENDPOINT/TTS_VOICE_EN it has
+	// always had.
+	TTSVoices map[string]TTSVoice
 	// TTSPath is the path Piper serves synthesis on. Piper moved it from "/" to
 	// "/synthesize" in 1.6.0 with an unchanged request body, so this is a
 	// version knob, not a feature: millenia's older server keeps the default,
@@ -56,6 +63,12 @@ type Config struct {
 	AllowedSubs string
 }

+// TTSVoice is one Piper instance and the single voice it has loaded.
+type TTSVoice struct {
+	Endpoint string
+	Voice    string
+}
+
 // AuthEnabled reports whether real logins are configured. When false, Petal
 // resolves every request to the local user.
 func (c *Config) AuthEnabled() bool {
@@ -77,14 +90,12 @@ func Load() *Config {
 		LLMChatModel: env("LLM_CHAT_MODEL", ""),
 		LLMTimeout:   envDuration("LLM_TIMEOUT", 30*time.Second),

-		TTSEndpoint:   env("TTS_ENDPOINT", ""),
-		TTSEndpointZH: env("TTS_ENDPOINT_ZH", ""),
-		TTSVoiceEN:    env("TTS_VOICE_EN", "en_US-amy-medium"),
-		TTSVoiceZH:    env("TTS_VOICE_ZH", "zh_CN-huayan-medium"),
-		TTSPath:       env("TTS_PATH", "/"),
-		TTSCacheDir:   env("TTS_CACHE_DIR", "./data/tts"),
-		TTSTimeout:    envDuration("TTS_TIMEOUT", 15*time.Second),
-		TTSFormat:     env("TTS_AUDIO_FORMAT", "mp3"),
+		TTSEndpoint: env("TTS_ENDPOINT", ""),
+		TTSVoices:   ttsVoices(os.Environ()),
+		TTSPath:     env("TTS_PATH", "/"),
+		TTSCacheDir: env("TTS_CACHE_DIR", "./data/tts"),
+		TTSTimeout:  envDuration("TTS_TIMEOUT", 15*time.Second),
+		TTSFormat:   env("TTS_AUDIO_FORMAT", "mp3"),

 		AuthentikURL:          env("AUTHENTIK_URL", ""),
 		AuthentikClientID:     env("AUTHENTIK_CLIENT_ID", ""),
@@ -93,6 +104,64 @@ func Load() *Config {
 	}
 }

+// ttsVoices reads the Piper instances out of an environment slice (as returned
+// by os.Environ) into a map keyed by base language tag.
+//
+// English is the unsuffixed pair, TTS_ENDPOINT + TTS_VOICE_EN, because that is
+// what every deployment already sets and read-aloud has always been English
+// first. Every other language is a TTS_ENDPOINT_<LANG>/TTS_VOICE_<LANG> pair,
+// discovered rather than enumerated — TTS_ENDPOINT_ZH is what millenia and the
+// VPS already use, and TTS_ENDPOINT_PT is all the Portuguese pair needs.
+//
+// <LANG> is the *base* tag: an environment variable name cannot hold the hyphen
+// in "pt-PT", and the handler routes on the base tag anyway (a request for
+// pt-PT, pt-BR or bare pt reaches the same instance, because there is only one
+// Portuguese voice loaded). A pair is ignored unless both halves are set: half
+// a configuration should read as "no voice for this language" and fall back to
+// the browser, not as an instance that answers every request with an error.
+func ttsVoices(environ []string) map[string]TTSVoice {
+	vals := make(map[string]string, len(environ))
+	for _, kv := range environ {
+		if k, v, ok := strings.Cut(kv, "="); ok {
+			vals[k] = v
+		}
+	}
+
+	voices := map[string]TTSVoice{}
+	add := func(lang, endpoint, voice string) {
+		endpoint = strings.TrimRight(strings.TrimSpace(endpoint), "/")
+		voice = strings.TrimSpace(voice)
+		if endpoint == "" || voice == "" {
+			return
+		}
+		voices[lang] = TTSVoice{Endpoint: endpoint, Voice: voice}
+	}
+
+	// The two languages that shipped before this was a map keep their voice
+	// defaults, so an existing deployment that names only the endpoints (as
+	// millenia's unit does) sounds exactly as it did.
+	voiceOr := func(key, fallback string) string {
+		if v := strings.TrimSpace(vals[key]); v != "" {
+			return v
+		}
+		return fallback
+	}
+
+	add("en", vals["TTS_ENDPOINT"], voiceOr("TTS_VOICE_EN", "en_US-amy-medium"))
+	for k, endpoint := range vals {
+		suffix, ok := strings.CutPrefix(k, "TTS_ENDPOINT_")
+		if !ok || suffix == "" {
+			continue
+		}
+		voice := vals["TTS_VOICE_"+suffix]
+		if suffix == "ZH" {
+			voice = voiceOr("TTS_VOICE_ZH", "zh_CN-huayan-medium")
+		}
+		add(strings.ToLower(suffix), endpoint, voice)
+	}
+	return voices
+}
+
 func env(key, fallback string) string {
 	if v := os.Getenv(key); v != "" {
 		return v
@@ -0,0 +1,83 @@
+package config
+
+import "testing"
+
+// The Piper instances are discovered from the environment rather than named in
+// code, so that a new pair costs a compose service and two .env lines. These
+// assert the discovery rule, including the two shapes that already exist in the
+// wild (millenia's systemd unit and the VPS compose file).
+func TestTTSVoicesDiscovery(t *testing.T) {
+	voices := ttsVoices([]string{
+		"TTS_ENDPOINT=http://piper-en:5000",
+		"TTS_VOICE_EN=en_US-amy-medium",
+		"TTS_ENDPOINT_ZH=http://piper-zh:5000/",
+		"TTS_VOICE_ZH=zh_CN-huayan-medium",
+		"TTS_ENDPOINT_PT=http://piper-pt:5000",
+		"TTS_VOICE_PT=pt_PT-tugão-medium",
+		// Noise that must not become a language.
+		"TTS_PATH=/synthesize",
+		"PATH=/usr/bin",
+	})
+
+	want := map[string]TTSVoice{
+		"en": {"http://piper-en:5000", "en_US-amy-medium"},
+		// The trailing slash is trimmed here so the synthesis path concatenates
+		// cleanly rather than producing a double slash at every call site.
+		"zh": {"http://piper-zh:5000", "zh_CN-huayan-medium"},
+		"pt": {"http://piper-pt:5000", "pt_PT-tugão-medium"},
+	}
+	if len(voices) != len(want) {
+		t.Fatalf("discovered %v, want %v", voices, want)
+	}
+	for lang, w := range want {
+		if voices[lang] != w {
+			t.Errorf("%s = %+v, want %+v", lang, voices[lang], w)
+		}
+	}
+}
+
+// Half a configuration is not a language. An endpoint with no voice (or the
+// reverse) must read as "no voice for this language" — a 404 the client answers
+// by falling back to Web Speech — rather than as an instance that exists and
+// errors on every request.
+func TestTTSVoicesIgnoresHalfConfiguredLanguages(t *testing.T) {
+	voices := ttsVoices([]string{
+		"TTS_ENDPOINT=http://piper-en:5000",
+		"TTS_VOICE_EN=en_US-amy-medium",
+		"TTS_ENDPOINT_FR=http://piper-fr:5000", // no TTS_VOICE_FR
+		"TTS_VOICE_ES=es_ES-davefx-medium",     // no TTS_ENDPOINT_ES
+	})
+	if _, ok := voices["fr"]; ok {
+		t.Errorf("fr routed with no voice configured")
+	}
+	if _, ok := voices["es"]; ok {
+		t.Errorf("es routed with no endpoint configured")
+	}
+	if len(voices) != 1 {
+		t.Errorf("discovered %v, want English only", voices)
+	}
+}
+
+// A deployment that predates the map names only the endpoints and relies on the
+// voice defaults; it must sound exactly as it did.
+func TestTTSVoicesKeepsTheOriginalDefaults(t *testing.T) {
+	voices := ttsVoices([]string{
+		"TTS_ENDPOINT=http://127.0.0.1:5005",
+		"TTS_ENDPOINT_ZH=http://127.0.0.1:5006",
+	})
+	if got := voices["en"].Voice; got != "en_US-amy-medium" {
+		t.Errorf("en voice = %q, want the default", got)
+	}
+	if got := voices["zh"].Voice; got != "zh_CN-huayan-medium" {
+		t.Errorf("zh voice = %q, want the default", got)
+	}
+}
+
+// Read-aloud is off when no English instance is configured; nothing else may
+// switch it on. (tts.New gates on TTSEndpoint, so a stray TTS_ENDPOINT_PT with
+// no English sibling must not produce a routable map that outlives that gate.)
+func TestTTSVoicesEmptyWithoutEndpoints(t *testing.T) {
+	if voices := ttsVoices([]string{"TTS_VOICE_EN=en_US-amy-medium"}); len(voices) != 0 {
+		t.Errorf("discovered %v, want none", voices)
+	}
+}