NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #1195 most downloaded on PyPI
Google Cloud Texttospeech API client library
Last release 3 days ago
01 Oct 2026
Ships fairly regularly
a new release about every 5 weeks
Nearly every release is documented
notes for 58 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
9 years old
72 releases · first in 2018
### Features * declare Python3.15 support
regenerate google-cloud-[t-w] packages
One column per quarter.
Support safety settings for Gemini voices and deprecate relax_safety_filters
markup in message .google.cloud.texttospeech.v1beta1.StreamingSynthesisInput is changed (c36aa6169035fdb14bf84b0e56e4f81291600b5a)advanced_voice_options in message .google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest is changed (c36aa6169035fdb14bf84b0e56e4f81291600b5a)markup in message .google.cloud.texttospeech.v1beta1.SynthesisInput is changed (c36aa6169035fdb14bf84b0e56e4f81291600b5a)relax_safety_filters in message .google.cloud.texttospeech.v1beta1.AdvancedVoiceOptions is changed (c36aa6169035fdb14bf84b0e56e4f81291600b5a)enable_textnorm for Gemini voices. (c36aa6169035fdb14bf84b0e56e4f81291600b5a)relax_safety_filters (c36aa6169035fdb14bf84b0e56e4f81291600b5a)advanced_voice_options as optional. (c36aa6169035fdb14bf84b0e56e4f81291600b5a)update image to us-central1-docker.pkg.dev/cloud-sdk-librarian-prod/images-prod/python-librarian-generator@sha256:f5426423676c75008c2135037e7b98f78cbb
auto-enable mTLS when supported certificates are detected
add relax_safety_filters proto field for Gemini TTS
relax_safety_filters proto field for Gemini TTS (1dbd0988eebdb63c7f08737d45f9ff67735ab396)relax_safety_filters proto field for Gemini TTS (1dbd0988eebdb63c7f08737d45f9ff67735ab396)Deprecate credentials_file argument
firestore: add BSONInt32 support
[google-cloud-texttospeech] add Gemini TTS Multispeaker API fields
### Features * Add prompt to SynthesisInput
[google-cloud-texttospeech] Support promptable voices by specifying a model name and a prompt
AUDIO_ENCODING_UNSPECIFIED in enum AudioEncoding is changed (a610c53)OGG_OPUS in enum AudioEncoding is changed (a610c53)PCM in enum AudioEncoding is changed (a610c53)PHONETIC_ENCODING_IPA in enum PhoneticEncoding is changed (a610c53)PHONETIC_ENCODING_X_SAMPA in enum PhoneticEncoding is changed (a610c53)audio_encoding in message .google.cloud.texttospeech.v1beta1.StreamingAudioConfig is changed (a610c53)custom_pronunciations in message .google.cloud.texttospeech.v1beta1.SynthesisInput is changed (a610c53)low_latency_journey_synthesis in message .google.cloud.texttospeech.v1beta1.AdvancedVoiceOptions is changed (a610c53)phrase in message .google.cloud.texttospeech.v1beta1.CustomPronunciationParams is changed (a610c53)pronunciations in message .google.cloud.texttospeech.v1beta1.CustomPronunciations is changed (a610c53)speaking_rate in message .google.cloud.texttospeech.v1beta1.AudioConfig is changed (a610c53)text in message .google.cloud.texttospeech.v1beta1.StreamingSynthesisInput is changed (a610c53)voice_clone in message .google.cloud.texttospeech.v1beta1.VoiceSelectionParams is changed (a610c53)MultiSpeakerMarkup is changed (a610c53)StreamingSynthesize in service TextToSpeech is changed (a610c53)Support markup input for Cloud TTS Chirp 3: HD voice synthesis
Support HD voice custom pronunciations
OGG_OPUS in enum AudioEncoding is changed (4da3cf3)PCM in enum AudioEncoding is changed (4da3cf3)PHONETIC_ENCODING_IPA in enum PhoneticEncoding is changed (4da3cf3)PHONETIC_ENCODING_X_SAMPA in enum PhoneticEncoding is changed (4da3cf3)audio_encoding in message .google.cloud.texttospeech.v1.StreamingAudioConfig is changed (4da3cf3)custom_pronunciations in message .google.cloud.texttospeech.v1.SynthesisInput is changed (4da3cf3)low_latency_journey_synthesis in message .google.cloud.texttospeech.v1.AdvancedVoiceOptions is changed (4da3cf3)phrase in message .google.cloud.texttospeech.v1.CustomPronunciationParams is changed (4da3cf3)pronunciations in message .google.cloud.texttospeech.v1.CustomPronunciations is changed (4da3cf3)text in message .google.cloud.texttospeech.v1.StreamingSynthesisInput is changed (4da3cf3)voice_clone in message .google.cloud.texttospeech.v1.VoiceSelectionParams is changed (4da3cf3)MultiSpeakerMarkup is changed (4da3cf3)StreamingSynthesize in service TextToSpeech is changed (4da3cf3)remove setup.cfg configuration for creating universal wheels
update API sources and regenerate
[google-cloud-texttospeech] StreamingSynthesize now supports opus
[google-cloud-texttospeech] StreamingSynthesize now supports opus
Add support for opt-in debug logging
disable universe-domain validation
add multi-speaker markup, which allows generating dialogue between multiple speakers
Add multi-speaker markup, which allows generating dialogue between multiple speakers
[google-cloud-texttospeech] Add brand voice lite
Add CustomPronunciationParams for upcoming feature work
[google-cloud-texttospeech] update Long Audio capabilities to include SSML
[google-cloud-texttospeech] update Long Audio capabilities to include SSML
A new method StreamingSynthesize is added to service TextToSpeech
Retry and timeout values do not propagate in requests during pagination
### Bug Fixes * Allow Protobuf 5.x
deps: Exclude google-auth 2.24.0 and 2.25.0
deps: [Many APIs] Require google-api-core>=1.34.1
Add google-auth as a direct dependency
Allow users to explicitly configure universe domain
Deprecate the custom voice usage field
Introduce compatibility with native namespace packages
Nothing published for this version
### Documentation * Minor formatting
Add context manager return types
### Features * Add support for python 3.11
update API sources and regenerate
google.cloud.texttospeech.__version__ (a2a534c)### Bug Fixes * deps: Allow protobuf 3.19.5
deps: Require protobuf >= 3.20.2
deps: require proto-plus >= 1.22.0
deps: require protobuf <4.0.0dev
2.11.0 (2026-09-29) Features declare Python3.15 support
handwritten: centralize CONTRIBUTING.rst pointers
### Documentation * add generated snippets
Added virtualenv comment for clarity
### Features * update v1 proto
### Features * v1beta1: add CustomVoiceParams (#215) (6a18d0f) ### Documentation * fix docstring formatting
deps: drop packaging dependency
2.7.0 (2026-09-29) Features declare Python3.15 support
add context manager support in client
add 'dict' annotation type to 'request'
deps: pin 'google-{api,cloud}-core', 'google-auth' to allow 2.x versions
omit mention of Python 2.7 in 'CONTRIBUTING.rst' (#1127) (#150) (d2954ba), closes #1126
support self-signed JWT flow for service accounts
add from_service_account_info to clients
from_service_account_info to clients (139e6e8)Your coding agent can read these notes before it upgrades. Set up the MCP server →