Samples: Synthesize Speech (text, ssml, string, local file)

samples/resources/hello.ssml

@@ -0,0 +1,7 @@
+<?xml version="1.0"?>
+  <speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis"
+  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  xsi:schemaLocation="http://www.w3.org/2001/10/synthesis
+  http://www.w3.org/TR/speech-synthesis/synthesis.xsd" xml:lang="en-US">
+  Hello there.
+</speak>

samples/resources/hello.txt

@@ -0,0 +1 @@
+Hello there.

samples/system-test/textToSpeech.test.js

@@ -0,0 +1,97 @@
+/**
+ * Copyright 2018, Google, Inc.
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+'use strict';
+
+const fs = require(`fs`);
+const path = require(`path`);
+const test = require(`ava`);
+const tools = require(`@google-cloud/nodejs-repo-tools`);
+
+const cmd = `node textToSpeech.js`;
+const cwd = path.join(__dirname, `..`);
+const text = `Hello there.`;
+const ssml = `<?xml version="1.0"?>
+<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis"
+xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+xsi:schemaLocation="http://www.w3.org/2001/10/synthesis
+http://www.w3.org/TR/speech-synthesis/synthesis.xsd" xml:lang="en-US">
+Hello there.
+</speak>`;
+const outputFile = `test-output.mp3`;
+const files = [
+  `hello.txt`,
+  `hello.ssml`,
+].map(name => {
+  return {
+    name,
+    localPath: path.resolve(path.join(__dirname, `../resources/${name}`)),
+  };
+});
+
+test.before(tools.checkCredentials);
+
+test.after.always(async () => {
+  await fs.unlink(outputFile);
+});
+
+test(`should list voice`, async t => {
+  const output = await tools.runAsync(
+    `${cmd} list-voices`,
+    cwd
+  );
+  t.true(output.includes(`SSML Gender: FEMALE`));
+  t.true(output.includes(`Natural Sample Rate Hertz: 24000`));
+});
+
+test(`should synthesize audio from text`, async t => {
+  t.false(fs.existsSync(outputFile));
+  const output = await tools.runAsync(
+    `${cmd} synthesize-text '${text}' --outputFile '${outputFile}'`,
+    cwd
+  );
+  t.true(output.includes(`Saved synthesized text to local audio file ${outputFile}`));
+  t.true(fs.existsSync(outputFile));
+});
+
+test(`should synthesize audio from ssml`, async t => {
+  t.false(fs.existsSync(outputFile));
+  const output = await tools.runAsync(
+    `${cmd} synthesize-ssml '${ssml}' --outputFile '${outputFile}'`,
+    cwd
+  );
+  t.true(output.includes(`Saved synthesized text to local audio file ${outputFile}`));
+  t.true(fs.existsSync(outputFile));
+});
+
+test(`should synthesize audio from text file`, async t => {
+  t.false(fs.existsSync(outputFile));
+  const output = await tools.runAsync(
+    `${cmd} synthesize-text-file '${files[0].localPath}' --outputFile '${outputFile}'`,
+    cwd
+  );
+  t.true(output.includes(`Saved synthesized text to local audio file ${outputFile}`));
+  t.true(fs.existsSync(outputFile));
+});
+
+test(`should synthesize audio from ssml file`, async t => {
+  t.false(fs.existsSync(outputFile));
+  const output = await tools.runAsync(
+    `${cmd} synthesize-ssml-file '${files[1].localPath}' --outputFile '${outputFile}'`,
+    cwd
+  );
+  t.true(output.includes(`Saved synthesized text to local audio file ${outputFile}`));
+  t.true(fs.existsSync(outputFile));
+});

samples/textToSpeech.js

@@ -42,6 +42,134 @@ function listVoices() {
   // [END tts_list_voices]
 }
 
+function synthesizeText(text, outputFile) {
+  // [START tts_synthesize_text]
+  const textToSpeech = require('@google-cloud/text-to-speech');
+  const fs = require('fs');
+
+  var client = new textToSpeech.TextToSpeechClient();
+
+  /**
+   * TODO(developer): Uncomment the following lines before running the sample.
+   */
+  // const text = 'Text to synthesize, eg. hello';
+  // const outputFile = 'Local path to save audio file to, e.g. output.mp3';
+
+  var request = {
+    input: { text: text },
+    voice: { languageCode: 'en-US', ssmlGender: 'FEMALE' },
+    audioConfig: { audioEncoding: 'MP3' }
+  };
+
+  client.synthesizeSpeech(request)
+  .then(results => {
+      const audioContent = results[0].audioContent;
+
+      fs.writeFileSync(outputFile, audioContent, 'binary');
+      console.log(`Saved synthesized text to local audio file ${outputFile}`);
+    })
+    .catch(err => {
+      console.error('ERROR:', err);
+    });
+  // [END tts_synthesize_text]
+}
+
+function synthesizeSsml(ssml, outputFile) {
+  // [START tts_synthesize_ssml]
+  const textToSpeech = require('@google-cloud/text-to-speech');
+  const fs = require('fs');
+
+  var client = new textToSpeech.TextToSpeechClient();
+
+  /**
+   * TODO(developer): Uncomment the following lines before running the sample.
+   */
+  // const ssml = 'SSML to synthesize, eg. <?xml version="1.0"?><speak...';
+  // const outputFile = 'Local path to save audio file to, e.g. output.mp3';
+
+  var request = {
+    input: { ssml: ssml },
+    voice: { languageCode: 'en-US', ssmlGender: 'FEMALE' },
+    audioConfig: { audioEncoding: 'MP3' }
+  };
+
+  client.synthesizeSpeech(request)
+  .then(results => {
+      const audioContent = results[0].audioContent;
+
+      fs.writeFileSync(outputFile, audioContent, 'binary');
+      console.log(`Saved synthesized text to local audio file ${outputFile}`);
+    })
+    .catch(err => {
+      console.error('ERROR:', err);
+    });
+  // [END tts_synthesize_ssml]
+}
+
+function synthesizeTextFile(textFile, outputFile) {
+  // [START tts_synthesize_text_file]
+  const textToSpeech = require('@google-cloud/text-to-speech');
+  const fs = require('fs');
+
+  var client = new textToSpeech.TextToSpeechClient();
+
+  /**
+   * TODO(developer): Uncomment the following lines before running the sample.
+   */
+  // const textFile = 'Local path to text file, eg. input.txt';
+  // const outputFile = 'Local path to save audio file to, e.g. output.mp3';
+
+  var request = {
+    input: { text: fs.readFileSync(textFile) },
+    voice: { languageCode: 'en-US', ssmlGender: 'FEMALE' },
+    audioConfig: { audioEncoding: 'MP3' }
+  };
+
+  client.synthesizeSpeech(request)
+  .then(results => {
+      const audioContent = results[0].audioContent;
+
+      fs.writeFileSync(outputFile, audioContent, 'binary');
+      console.log(`Saved synthesized text to local audio file ${outputFile}`);
+    })
+    .catch(err => {
+      console.error('ERROR:', err);
+    });
+  // [END tts_synthesize_text_file]
+}
+
+function synthesizeSsmlFile(ssmlFile, outputFile) {
+  // [START tts_synthesize_ssml_file]
+  const textToSpeech = require('@google-cloud/text-to-speech');
+  const fs = require('fs');
+
+  var client = new textToSpeech.TextToSpeechClient();
+
+  /**
+   * TODO(developer): Uncomment the following lines before running the sample.
+   */
+  // const ssmlFile = 'Local path to SSML file, eg. input.ssml';
+  // const outputFile = 'Local path to save audio file to, e.g. output.mp3';
+
+  var request = {
+    input: { ssml: fs.readFileSync(ssmlFile) },
+    voice: { languageCode: 'en-US', ssmlGender: 'FEMALE' },
+    audioConfig: { audioEncoding: 'MP3' }
+  };
+
+  client.synthesizeSpeech(request)
+  .then(results => {
+      const audioContent = results[0].audioContent;
+
+      fs.writeFileSync(outputFile, audioContent, 'binary');
+      console.log(`Saved synthesized text to local audio file ${outputFile}`);
+    })
+    .catch(err => {
+      console.error('ERROR:', err);
+    });
+  // [END tts_synthesize_ssml_file]
+}
+
 require(`yargs`) // eslint-disable-line
   .demand(1)
   .command(
@@ -50,7 +178,44 @@ require(`yargs`) // eslint-disable-line
     {},
     opts => listVoices()
   )
+  .command(
+    `synthesize-text <text>`,
+    `Synthesizes audio file from text`,
+    {},
+    opts => synthesizeText(opts.text, opts.outputFile)
+  )
+  .command(
+    `synthesize-ssml <ssml>`,
+    `Synthesizes audio file from SSML`,
+    {},
+    opts => synthesizeSsml(opts.ssml, opts.outputFile)
+  )
+  .command(
+    `synthesize-text-file <textFile>`,
+    `Synthesizes audio file from text in a file`,
+    {},
+    opts => synthesizeTextFile(opts.textFile, opts.outputFile)
+  )
+  .command(
+    `synthesize-ssml-file <ssmlFile>`,
+    `Synthesizes audio file from SSML in a file`,
+    {},
+    opts => synthesizeSsmlFile(opts.ssmlFile, opts.outputFile)
+  )
+  .options({
+    outputFile: {
+      alias: 'o',
+      default: 'output.mp3',
+      global: true,
+      requiresArg: true,
+      type: 'string'
+    }
+  })
   .example(`node $0 list-voices`)
+  .example(`node $0 synthesize-text "hello" -o hello.mp3`)
+  .example(`node $0 synthesize-ssml "<?xml..." -o hello.mp3`)
+  .example(`node $0 synthesize-text-file filename.txt -o output.mp3`)
+  .example(`node $0 synthesize-ssml-file filename.ssml -o output.mp3`)
   .wrap(120)
   .recommendCommands()
   .epilogue(`For more information, see https://cloud.google.com/text-to-speech/docs`)