add ipa transcription funtionality

.github/workflows/main.yml

@@ -0,0 +1,31 @@
+name: ci
+
+on:
+  push:
+    branches:
+      - "main"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Build and push
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ${{ secrets.DOCKERHUB_USERNAME }}/clockbox:latest

.github/workflows/main2.yml

@@ -0,0 +1,31 @@
+name: ci
+
+on:
+  push:
+    branches:
+      - "master"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Build and push
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ${{ secrets.DOCKERHUB_USERNAME }}/espeak-ipa:latest

Dockerfile

@@ -1,20 +1,19 @@
-FROM gliderlabs/alpine:3.1
-RUN apk-install espeak opus lame flac wget && \
- apk del libstdc++ 
-
+FROM alpine:3.17.2
+RUN apk add --no-cache espeak opus lame flac wget && \
+    apk del libstdc++
 RUN cd /tmp && \
-wget https://downloads.xiph.org/releases/opus/opus-tools-0.1.9.tar.gz --no-check-certificate && \
-    tar xzf opus-tools-0.1.9.tar.gz && \
+    wget https://downloads.xiph.org/releases/opus/opus-tools-0.1.9.tar.gz --no-check-certificate && \
+tar xzf opus-tools-0.1.9.tar.gz && \
     cd opus-tools-0.1.9/ && \
-    apk-install build-base flac-dev opus-dev libogg-dev && \
+    apk add --no-cache build-base flac-dev opus-dev libogg-dev && \
     ./configure && \
     make && \
     make install && \
     rm -rf /tmp/* && \
     apk del build-base flac-dev opus-dev libogg-dev
 COPY server.go /tmp/
 RUN cd /tmp && \
-    apk-install go && \
+    apk add --no-cache go && \
     go build -o /server server.go && \
     apk del go && \
     rm /tmp/server.go

README.md

@@ -27,7 +27,7 @@ GET /speech?text=<utterance>
             [&pitch=<0,99; default 50>]
             [&speed=<80,450; default 175 wpm>]
             [&voice=<name; default en>]
-            [&encoding=<mp3|opus; default mp3>]
+            [&encoding=<mp3|opus|wav; default mp3>]
 ```
 
 Response:

server.go

@@ -117,7 +117,7 @@ func buildEncodeCmd(values *url.Values, w *http.ResponseWriter) (cmd *exec.Cmd,
 }
 
 // Handles a request for synthesized speech. Build the synthesizer and encoder
-// comands. Pipe the first to the second. Pipe the encoded stream out as the
+// commands. Pipe the first to the second. Pipe the encoded stream out as the
 // response. Supports URL arguments:
 // text: string to synthesize (required)
 // pitch: [0, 99] default: 50
@@ -198,8 +198,8 @@ func voicesHandler(w http.ResponseWriter, r *http.Request) {
 		}
 
 		voices := new(Voices)
-		// leave out the header value
-		voices.Names = strings.Split(voicesBuf.String(), "\n")[1:]
+		// leave out the header value and trailing empty line
+		voices.Names = strings.Split(strings.TrimSpace(voicesBuf.String()), "\n")[1:]
 
 		js, err := json.Marshal(voices)
 		if err != nil {
@@ -214,9 +214,44 @@ func voicesHandler(w http.ResponseWriter, r *http.Request) {
 	w.Write(cachedVoicesJSON)
 }
 
+// Handles a request to get the ipa of a word.
+func ipaHandler(w http.ResponseWriter, r *http.Request) {
+
+	args := []string{"--ipa"}
+
+	values := r.URL.Query()
+
+	// text is the only required parameter
+	text := values.Get("text")
+	if len(text) == 0 {
+		err := errors.New("Missing required parameter: text")
+		http.Error(w, err.Error(), 400)
+		return
+	} else {
+		args = append(args, text)
+	}
+
+	// voice
+	voice := values.Get("voice")
+	if len(voice) > 0 {
+		args = append(args, "-v")
+		args = append(args, voice)
+	}
+
+	var ipaStr, err = exec.Command("espeak", args...).Output()
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusInternalServerError)
+		return
+	}
+	w.Header().Set("Content-Type", "application/json")
+
+	w.Write(ipaStr)
+}
+
 func main() {
 	http.HandleFunc("/speech", speechHandler)
 	http.HandleFunc("/voices", voicesHandler)
+	http.HandleFunc("/ipa", ipaHandler)
 
 	err := http.ListenAndServe(":8080", nil)
 	if err != nil {

server_test.go

@@ -0,0 +1,37 @@
+package main
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+)
+
+func TestVoicesHandler(t *testing.T) {
+	// Avoid external command execution by setting the cached response
+	cachedVoicesJSON = []byte(`{"names": ["en"]}`)
+
+	mux := http.NewServeMux()
+	mux.HandleFunc("/voices", voicesHandler)
+	ts := httptest.NewServer(mux)
+	defer ts.Close()
+
+	resp, err := http.Get(ts.URL + "/voices")
+	if err != nil {
+		t.Fatalf("failed to GET /voices: %v", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("expected status 200, got %d", resp.StatusCode)
+	}
+
+	var data map[string]interface{}
+	if err := json.NewDecoder(resp.Body).Decode(&data); err != nil {
+		t.Fatalf("failed to decode JSON: %v", err)
+	}
+
+	if _, ok := data["names"]; !ok {
+		t.Fatalf("response JSON missing 'names' key")
+	}
+}