Stay organized with collectionsSave and categorize content based on your preferences.
This page describes how to create a dialogue with multiple speakers
created by Text-to-Speech.
You can generate audio with multiple speakers to create a dialogue. This can be
useful for interviews, interactive storytelling, video games,
e-learning platforms, and accessibility solutions.
The following voice is supported for audio with multiple speakers:
en-US-Studio-Multispeaker
speaker:R
speaker:S
speaker:T
speaker:U
Example. This sample is audio that was generated using multiple speakers.
Example of how to use multi-speaker markup
This is an example that demonstrates how to use multi-speaker markup.
"""Synthesizes speech for multiple speakers.Make sure to be working in a virtual environment."""fromgoogle.cloudimporttexttospeech_v1beta1astexttospeech# Instantiates a clientclient=texttospeech.TextToSpeechClient()multi_speaker_markup=texttospeech.MultiSpeakerMarkup(turns=[texttospeech.MultiSpeakerMarkup.Turn(text="I've heard that the Google Cloud multi-speaker audio generation sounds amazing!",speaker="R",),texttospeech.MultiSpeakerMarkup.Turn(text="Oh? What's so good about it?",speaker="S"),texttospeech.MultiSpeakerMarkup.Turn(text="Well..",speaker="R"),texttospeech.MultiSpeakerMarkup.Turn(text="Well what?",speaker="S"),texttospeech.MultiSpeakerMarkup.Turn(text="Well, you should find it out by yourself!",speaker="R"),texttospeech.MultiSpeakerMarkup.Turn(text="Alright alright, let's try it out!",speaker="S"),])# Set the text input to be synthesizedsynthesis_input=texttospeech.SynthesisInput(multi_speaker_markup=multi_speaker_markup)# Build the voice request, select the language code ('en-US') and the voicevoice=texttospeech.VoiceSelectionParams(language_code="en-US",name="en-US-Studio-MultiSpeaker")# Select the type of audio file you want returnedaudio_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 typeresponse=client.synthesize_speech(input=synthesis_input,voice=voice,audio_config=audio_config)# The response's audio_content is binary.withopen("output.mp3","wb")asout:# Write the response to the output file.out.write(response.audio_content)print('Audio content written to file "output.mp3"')
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Generate dialogue with multiple speakers\n\n| **Note:** This feature is only available to projects in allowlist. Please contact us if you want to use this feature.\n\nThis page describes how to create a dialogue with multiple speakers\ncreated by Text-to-Speech.\n\nYou can generate audio with multiple speakers to create a dialogue. This can be\nuseful for interviews, interactive storytelling, video games,\ne-learning platforms, and accessibility solutions.\n\nThe following voice is supported for audio with multiple speakers:\n\n- `en-US-Studio-Multispeaker`\n - speaker: `R`\n - speaker: `S`\n - speaker: `T`\n - speaker: `U`\n\nYour browser does not support the audio element. \n\n*Example. This sample is audio that was generated using multiple speakers.* \n| **Note:** This feature supports a maximum of two speakers. It's an experimental offering and not in the [list of voices](/text-to-speech/docs/list-voices).\n\nExample of how to use multi-speaker markup\n------------------------------------------\n\nThis is an example that demonstrates how to use multi-speaker markup. \n\n### Python\n\n\nTo learn how to install and use the client library for Text-to-Speech, see\n[Text-to-Speech client libraries](/text-to-speech/docs/libraries).\n\n\nFor more information, see the\n[Text-to-Speech Python API\nreference documentation](/python/docs/reference/texttospeech/latest).\n\n\nTo authenticate to Text-to-Speech, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n \"\"\"Synthesizes speech for multiple speakers.\n Make sure to be working in a virtual environment.\n \"\"\"\n from google.cloud import texttospeech_v1beta1 as texttospeech\n\n # Instantiates a client\n client = texttospeech.TextToSpeechClient()\n\n multi_speaker_markup = texttospeech.MultiSpeakerMarkup(\n turns=[\n texttospeech.MultiSpeakerMarkup.Turn(\n text=\"I've heard that the Google Cloud multi-speaker audio generation sounds amazing!\",\n speaker=\"R\",\n ),\n texttospeech.MultiSpeakerMarkup.Turn(\n text=\"Oh? What's so good about it?\", speaker=\"S\"\n ),\n texttospeech.MultiSpeakerMarkup.Turn(text=\"Well..\", speaker=\"R\"),\n texttospeech.MultiSpeakerMarkup.Turn(text=\"Well what?\", speaker=\"S\"),\n texttospeech.MultiSpeakerMarkup.Turn(\n text=\"Well, you should find it out by yourself!\", speaker=\"R\"\n ),\n texttospeech.MultiSpeakerMarkup.Turn(\n text=\"Alright alright, let's try it out!\", speaker=\"S\"\n ),\n ]\n )\n\n # Set the text input to be synthesized\n synthesis_input = texttospeech.SynthesisInput(\n multi_speaker_markup=multi_speaker_markup\n )\n\n # Build the voice request, select the language code ('en-US') and the voice\n voice = texttospeech.VoiceSelectionParams(\n language_code=\"en-US\", name=\"en-US-Studio-MultiSpeaker\"\n )\n\n # Select the type of audio file you want returned\n audio_config = texttospeech.AudioConfig(\n audio_encoding=texttospeech.AudioEncoding.MP3\n )\n\n # Perform the text-to-speech request on the text input with the selected\n # voice parameters and audio file type\n response = client.synthesize_speech(\n input=synthesis_input, voice=voice, audio_config=audio_config\n )\n\n # The response's audio_content is binary.\n with open(\"output.mp3\", \"wb\") as out:\n # Write the response to the output file.\n out.write(response.audio_content)\n print('Audio content written to file \"output.mp3\"')\n\n\u003cbr /\u003e"]]
