Merge remote-tracking branch 'migration/main' into python-texttospeec…

…h-migration

texttospeech/snippets/audio_profile.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python
+
+# Copyright 2018 Google LLC. All Rights Reserved.
+#
+# 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.
+
+"""Google Cloud Text-To-Speech API sample application for audio profile.
+
+Example usage:
+    python audio_profile.py --text "hello" --effects_profile_id
+        "telephony-class-application" --output "output.mp3"
+"""
+
+import argparse
+
+
+# [START tts_synthesize_text_audio_profile]
+# [START tts_synthesize_text_audio_profile_beta]
+def synthesize_text_with_audio_profile(text, output, effects_profile_id):
+    """Synthesizes speech from the input string of text."""
+    from google.cloud import texttospeech
+
+    client = texttospeech.TextToSpeechClient()
+
+    input_text = texttospeech.SynthesisInput(text=text)
+
+    # Note: the voice can also be specified by name.
+    # Names of voices can be retrieved with client.list_voices().
+    voice = texttospeech.VoiceSelectionParams(language_code="en-US")
+
+    # Note: you can pass in multiple effects_profile_id. They will be applied
+    # in the same order they are provided.
+    audio_config = texttospeech.AudioConfig(
+        audio_encoding=texttospeech.AudioEncoding.MP3,
+        effects_profile_id=[effects_profile_id],
+    )
+
+    response = client.synthesize_speech(
+        input=input_text, voice=voice, audio_config=audio_config
+    )
+
+    # The response's audio_content is binary.
+    with open(output, "wb") as out:
+        out.write(response.audio_content)
+        print('Audio content written to file "%s"' % output)
+
+
+# [END tts_synthesize_text_audio_profile_beta]
+# [END tts_synthesize_text_audio_profile]
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
+    )
+    parser.add_argument("--output", help="The output mp3 file.")
+    parser.add_argument("--text", help="The text from which to synthesize speech.")
+    parser.add_argument(
+        "--effects_profile_id", help="The audio effects profile id to be applied."
+    )
+
+    args = parser.parse_args()
+
+    synthesize_text_with_audio_profile(args.text, args.output, args.effects_profile_id)

texttospeech/snippets/audio_profile_test.py

@@ -0,0 +1,33 @@
+# Copyright 2018, Google, LLC.
+# 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.
+
+import os
+import os.path
+
+import audio_profile
+
+TEXT = "hello"
+OUTPUT = "output.mp3"
+EFFECTS_PROFILE_ID = "telephony-class-application"
+
+
+def test_audio_profile(capsys):
+    if os.path.exists(OUTPUT):
+        os.remove(OUTPUT)
+    assert not os.path.exists(OUTPUT)
+    audio_profile.synthesize_text_with_audio_profile(TEXT, OUTPUT, EFFECTS_PROFILE_ID)
+    out, err = capsys.readouterr()
+
+    assert ('Audio content written to file "%s"' % OUTPUT) in out
+    assert os.path.exists(OUTPUT)
+    os.remove(OUTPUT)

texttospeech/snippets/list_voices.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python
+
+# Copyright 2018 Google Inc. All Rights Reserved.
+#
+# 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.
+
+"""Google Cloud Text-To-Speech API sample application.
+
+Example usage:
+    python list_voices.py
+"""
+
+
+# [START tts_list_voices]
+def list_voices():
+    """Lists the available voices."""
+    from google.cloud import texttospeech
+
+    client = texttospeech.TextToSpeechClient()
+
+    # Performs the list voices request
+    voices = client.list_voices()
+
+    for voice in voices.voices:
+        # Display the voice's name. Example: tpc-vocoded
+        print(f"Name: {voice.name}")
+
+        # Display the supported language codes for this voice. Example: "en-US"
+        for language_code in voice.language_codes:
+            print(f"Supported language: {language_code}")
+
+        ssml_gender = texttospeech.SsmlVoiceGender(voice.ssml_gender)
+
+        # Display the SSML Voice Gender
+        print(f"SSML Voice Gender: {ssml_gender.name}")
+
+        # Display the natural sample rate hertz for this voice. Example: 24000
+        print(f"Natural Sample Rate Hertz: {voice.natural_sample_rate_hertz}\n")
+
+
+# [END tts_list_voices]
+
+
+if __name__ == "__main__":
+    list_voices()

texttospeech/snippets/list_voices_test.py

@@ -0,0 +1,23 @@
+# 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.
+
+import list_voices
+
+
+def test_list_voices(capsys):
+    list_voices.list_voices()
+    out, err = capsys.readouterr()
+
+    assert "en-US" in out
+    assert "SSML Voice Gender: MALE" in out
+    assert "SSML Voice Gender: FEMALE" in out

texttospeech/snippets/quickstart.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+
+# Copyright 2018 Google Inc. All Rights Reserved.
+#
+# 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.
+
+"""Google Cloud Text-To-Speech API sample application .
+
+Example usage:
+    python quickstart.py
+"""
+
+
+def run_quickstart():
+    # [START tts_quickstart]
+    """Synthesizes speech from the input string of text or ssml.
+    Make sure to be working in a virtual environment.
+
+    Note: ssml must be well-formed according to:
+        https://www.w3.org/TR/speech-synthesis/
+    """
+    from google.cloud import texttospeech
+
+    # Instantiates a client
+    client = texttospeech.TextToSpeechClient()
+
+    # Set the text input to be synthesized
+    synthesis_input = texttospeech.SynthesisInput(text="Hello, World!")
+
+    # Build the voice request, select the language code ("en-US") and the ssml
+    # voice gender ("neutral")
+    voice = texttospeech.VoiceSelectionParams(
+        language_code="en-US", ssml_gender=texttospeech.SsmlVoiceGender.NEUTRAL
+    )
+
+    # Select the type of audio file you want returned
+    audio_config = texttospeech.AudioConfig(
+        audio_encoding=texttospeech.AudioEncoding.MP3
+    )
+
+    # Perform the text-to-speech request on the text input with the selected
+    # voice parameters and audio file type
+    response = client.synthesize_speech(
+        input=synthesis_input, voice=voice, audio_config=audio_config
+    )
+
+    # The response's audio_content is binary.
+    with open("output.mp3", "wb") as out:
+        # Write the response to the output file.
+        out.write(response.audio_content)
+        print('Audio content written to file "output.mp3"')
+    # [END tts_quickstart]
+
+
+if __name__ == "__main__":
+    run_quickstart()

texttospeech/snippets/requirements-test.txt

@@ -0,0 +1 @@
+pytest==7.2.0

texttospeech/snippets/requirements.txt

@@ -0,0 +1,2 @@
+future==0.18.2
+google-cloud-texttospeech==2.12.3

texttospeech/snippets/resources/example.ssml

@@ -0,0 +1,4 @@
+<speak>123 Street Ln, Small Town, IL 12345 USA
+<break time="2s"/>1 Jenny St &amp; Number St, Tutone City, CA 86753
+<break time="2s"/>1 Piazza del Fibonacci, 12358 Pisa, Italy
+<break time="2s"/></speak>

texttospeech/snippets/resources/example.txt

@@ -0,0 +1,3 @@
+123 Street Ln, Small Town, IL 12345 USA
+1 Jenny St & Number St, Tutone City, CA 86753
+1 Piazza del Fibonacci, 12358 Pisa, Italy

texttospeech/snippets/resources/hello.ssml

@@ -0,0 +1 @@
+<speak>Hello there.</speak>

texttospeech/snippets/resources/hello.txt

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

texttospeech/snippets/ssml_addresses.py

@@ -0,0 +1,119 @@
+# Copyright 2019 Google LLC
+#
+# 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.
+
+
+# [START tts_ssml_address_imports]
+import html
+
+from google.cloud import texttospeech
+
+# [END tts_ssml_address_imports]
+
+
+# [START tts_ssml_address_audio]
+def ssml_to_audio(ssml_text, outfile):
+    # Generates SSML text from plaintext.
+    #
+    # Given a string of SSML text and an output file name, this function
+    # calls the Text-to-Speech API. The API returns a synthetic audio
+    # version of the text, formatted according to the SSML commands. This
+    # function saves the synthetic audio to the designated output file.
+    #
+    # Args:
+    # ssml_text: string of SSML text
+    # outfile: string name of file under which to save audio output
+    #
+    # Returns:
+    # nothing
+
+    # Instantiates a client
+    client = texttospeech.TextToSpeechClient()
+
+    # Sets the text input to be synthesized
+    synthesis_input = texttospeech.SynthesisInput(ssml=ssml_text)
+
+    # Builds the voice request, selects the language code ("en-US") and
+    # the SSML voice gender ("MALE")
+    voice = texttospeech.VoiceSelectionParams(
+        language_code="en-US", ssml_gender=texttospeech.SsmlVoiceGender.MALE
+    )
+
+    # Selects the type of audio file to return
+    audio_config = texttospeech.AudioConfig(
+        audio_encoding=texttospeech.AudioEncoding.MP3
+    )
+
+    # Performs the text-to-speech request on the text input with the selected
+    # voice parameters and audio file type
+    response = client.synthesize_speech(
+        input=synthesis_input, voice=voice, audio_config=audio_config
+    )
+
+    # Writes the synthetic audio to the output file.
+    with open(outfile, "wb") as out:
+        out.write(response.audio_content)
+        print("Audio content written to file " + outfile)
+    # [END tts_ssml_address_audio]
+
+
+# [START tts_ssml_address_ssml]
+def text_to_ssml(inputfile):
+    # Generates SSML text from plaintext.
+    # Given an input filename, this function converts the contents of the text
+    # file into a string of formatted SSML text. This function formats the SSML
+    # string so that, when synthesized, the synthetic audio will pause for two
+    # seconds between each line of the text file. This function also handles
+    # special text characters which might interfere with SSML commands.
+    #
+    # Args:
+    # inputfile: string name of plaintext file
+    #
+    # Returns:
+    # A string of SSML text based on plaintext input
+
+    # Parses lines of input file
+    with open(inputfile, "r") as f:
+        raw_lines = f.read()
+
+    # Replace special characters with HTML Ampersand Character Codes
+    # These Codes prevent the API from confusing text with
+    # SSML commands
+    # For example, '<' --> '&lt;' and '&' --> '&amp;'
+
+    escaped_lines = html.escape(raw_lines)
+
+    # Convert plaintext to SSML
+    # Wait two seconds between each address
+    ssml = "<speak>{}</speak>".format(
+        escaped_lines.replace("\n", '\n<break time="2s"/>')
+    )
+
+    # Return the concatenated string of ssml script
+    return ssml
+
+
+# [END tts_ssml_address_ssml]
+
+
+# [START tts_ssml_address_test]
+def main():
+    # test example address file
+    plaintext = "resources/example.txt"
+    ssml_text = text_to_ssml(plaintext)
+    ssml_to_audio(ssml_text, "resources/example.mp3")
+    # [END tts_ssml_address_test]
+
+
+if __name__ == "__main__":
+    main()