AWSSDK を使用して Amazon Polly でテキストから音声を合成する

次のコード例は、Amazon Polly でテキストから音声を合成する方法を示しています。

.NET

AWS SDK for .NET

注記

他にもありますGitHub。用例一覧を検索し、AWS コード例リポジトリでの設定と実行の方法を確認してください。

    using System;
    using System.IO;
    using System.Threading.Tasks;
    using Amazon.Polly;
    using Amazon.Polly.Model;

    public class SynthesizeSpeech
    {
        public static async Task Main()
        {
            string outputFileName = "speech.mp3";
            string text = "Twas brillig, and the slithy toves did gyre and gimbol in the wabe";

            var client = new AmazonPollyClient();
            var response = await PollySynthesizeSpeech(client, text);

            WriteSpeechToStream(response.AudioStream, outputFileName);
        }

        /// <summary>
        /// Calls the Amazon Polly SynthesizeSpeechAsync method to convert text
        /// to speech.
        /// </summary>
        /// <param name="client">The Amazon Polly client object used to connect
        /// to the Amazon Polly service.</param>
        /// <param name="text">The text to convert to speech.</param>
        /// <returns>A SynthesizeSpeechResponse object that includes an AudioStream
        /// object with the converted text.</returns>
        private static async Task<SynthesizeSpeechResponse> PollySynthesizeSpeech(IAmazonPolly client, string text)
        {
            var synthesizeSpeechRequest = new SynthesizeSpeechRequest()
            {
                OutputFormat = OutputFormat.Mp3,
                VoiceId = VoiceId.Joanna,
                Text = text,
            };

            var synthesizeSpeechResponse =
                await client.SynthesizeSpeechAsync(synthesizeSpeechRequest);

            return synthesizeSpeechResponse;
        }

        /// <summary>
        /// Writes the AudioStream returned from the call to
        /// SynthesizeSpeechAsync to a file in MP3 format.
        /// </summary>
        /// <param name="audioStream">The AudioStream returned from the
        /// call to the SynthesizeSpeechAsync method.</param>
        /// <param name="outputFileName">The full path to the file in which to
        /// save the audio stream.</param>
        private static void WriteSpeechToStream(Stream audioStream, string outputFileName)
        {
            var outputStream = new FileStream(
                outputFileName,
                FileMode.Create,
                FileAccess.Write);
            byte[] buffer = new byte[2 * 1024];
            int readBytes;

            while ((readBytes = audioStream.Read(buffer, 0, 2 * 1024)) > 0)
            {
                outputStream.Write(buffer, 0, readBytes);
            }

            // Flushes the buffer to avoid losing the last second or so of
            // the synthesized text.
            outputStream.Flush();
            Console.WriteLine($"Saved {outputFileName} to disk.");
        }
    }

AWSSDK を使用して Amazon Polly でスピーチマークを使用してテキストから音声を合成します。

    using System;
    using System.Collections.Generic;
    using System.IO;
    using System.Threading.Tasks;
    using Amazon.Polly;
    using Amazon.Polly.Model;

    public class SynthesizeSpeechMarks
    {
        public static async Task Main()
        {
            var client = new AmazonPollyClient();
            string outputFileName = "speechMarks.json";

            var synthesizeSpeechRequest = new SynthesizeSpeechRequest()
            {
                OutputFormat = OutputFormat.Json,
                SpeechMarkTypes = new List<string>
                {
                    SpeechMarkType.Viseme,
                    SpeechMarkType.Word,
                },
                VoiceId = VoiceId.Joanna,
                Text = "This is a sample text to be synthesized.",
            };

            try
            {
                using (var outputStream = new FileStream(outputFileName, FileMode.Create, FileAccess.Write))
                {
                    var synthesizeSpeechResponse = await client.SynthesizeSpeechAsync(synthesizeSpeechRequest);
                    var buffer = new byte[2 * 1024];
                    int readBytes;

                    var inputStream = synthesizeSpeechResponse.AudioStream;
                    while ((readBytes = inputStream.Read(buffer, 0, 2 * 1024)) > 0)
                    {
                        outputStream.Write(buffer, 0, readBytes);
                    }
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine($"Error: {ex.Message}");
            }
        }
    }

• API の詳細については、AWS SDK for .NETAPI SynthesizeSpeechリファレンスのを参照してください。

Python

SDK for Python (Boto3)

注記

他にもありますGitHub。用例一覧を検索し、AWS コード例リポジトリでの設定と実行の方法を確認してください。

class PollyWrapper:
    """Encapsulates Amazon Polly functions."""
    def __init__(self, polly_client, s3_resource):
        """
        :param polly_client: A Boto3 Amazon Polly client.
        :param s3_resource: A Boto3 Amazon Simple Storage Service (Amazon S3) resource.
        """
        self.polly_client = polly_client
        self.s3_resource = s3_resource
        self.voice_metadata = None

    def synthesize(
            self, text, engine, voice, audio_format, lang_code=None,
            include_visemes=False):
        """
        Synthesizes speech or speech marks from text, using the specified voice.

        :param text: The text to synthesize.
        :param engine: The kind of engine used. Can be standard or neural.
        :param voice: The ID of the voice to use.
        :param audio_format: The audio format to return for synthesized speech. When
                             speech marks are synthesized, the output format is JSON.
        :param lang_code: The language code of the voice to use. This has an effect
                          only when a bilingual voice is selected.
        :param include_visemes: When True, a second request is made to Amazon Polly
                                to synthesize a list of visemes, using the specified
                                text and voice. A viseme represents the visual position
                                of the face and mouth when saying part of a word.
        :return: The audio stream that contains the synthesized speech and a list
                 of visemes that are associated with the speech audio.
        """
        try:
            kwargs = {
                'Engine': engine,
                'OutputFormat': audio_format,
                'Text': text,
                'VoiceId': voice}
            if lang_code is not None:
                kwargs['LanguageCode'] = lang_code
            response = self.polly_client.synthesize_speech(**kwargs)
            audio_stream = response['AudioStream']
            logger.info("Got audio stream spoken by %s.", voice)
            visemes = None
            if include_visemes:
                kwargs['OutputFormat'] = 'json'
                kwargs['SpeechMarkTypes'] = ['viseme']
                response = self.polly_client.synthesize_speech(**kwargs)
                visemes = [json.loads(v) for v in
                           response['AudioStream'].read().decode().split() if v]
                logger.info("Got %s visemes.", len(visemes))
        except ClientError:
            logger.exception("Couldn't get audio stream.")
            raise
        else:
            return audio_stream, visemes

• API の詳細については、「AWSSDK for Python (Boto3) API リファレンス」のを参照してくださいSynthesizeSpeech。

Rust

SDK for Rust

注記

これはプレビューリリースの SDK に関するドキュメントです。SDK は変更される場合があり、本稼働環境では使用しないでください。

注記

他にもありますGitHub。用例一覧を検索し、AWS コード例リポジトリでの設定と実行の方法を確認してください。

async fn synthesize(client: &Client, filename: &str) -> Result<(), Error> {
    let content = fs::read_to_string(filename);

    let resp = client
        .synthesize_speech()
        .output_format(OutputFormat::Mp3)
        .text(content.unwrap())
        .voice_id(VoiceId::Joanna)
        .send()
        .await?;

    // Get MP3 data from response and save it
    let mut blob = resp
        .audio_stream
        .collect()
        .await
        .expect("failed to read data");

    let parts: Vec<&str> = filename.split('.').collect();
    let out_file = format!("{}{}", String::from(parts[0]), ".mp3");

    let mut file = tokio::fs::File::create(out_file)
        .await
        .expect("failed to create file");

    file.write_all_buf(&mut blob)
        .await
        .expect("failed to write to file");

    Ok(())
}

• API の詳細については、SDK for Rust API リファレンスSynthesizeSpeechの「AWSSDK for Rust API リファレンス」を参照してください。