Chirp 3: HD voices now support speech synthesis in Preview for the Chinese (Hong Kong) yue-HK language. For more information, see Chirp 3: Language Availability.

Chirp 3: HD voices now support speech synthesis in Preview for the Punjabi (pa-IN) language. For more information, see Chirp 3: Language Availability.

Our latest Gemini TTS models are now available in more regions.

• gemini-2.5-pro-tts: global, us, eu
• gemini-2.5-flash-tts: global, us, eu, and northamerica-northeast1
• gemini-2.5-flash-lite-preview-tts: global, us, eu, and northamerica-northeast1

For more information on how to take advantage of the extended regional availability, see the Gemini TTS page.

Chirp 3: HD voices now support speech synthesis in the following languages: bg-BG, cs-CZ, et-EE, el-GR, he-IL, hr-HR, hu-HU, lt-LT, lv-LV, ro-RO, sk-SK, sl-SI, and sr-RS. For more information, see Chirp 3: Language Availability.

Gemini TTS now supports relaxing safety filters for accounts with monthly invoiced billing. For more information, see the Gemini TTS page.

Feature

Gemini TTS now supports synthesis for streaming requests. For more information, see the Gemini TTS page.

Chirp 3: instant custom voice now supports voice cloning key generation in the eu and us regions. For more information, see the Chirp 3: instant custom voice page.

Chirp 3 HD now supports speech synthesis using SSML input. Supported SSML tags are: <phoneme>, <p>, <s>, <sub>, and <say-as>. For more information, see Chirp 3 HD: SSML support.

We just released Gemini-2.5 TTS Flash (gemini-2.5-flash-tts) and Pro (gemini-2.5-pro-tts) in GA with support for 30 speakers in 80 or more locales. The latest models enable granular control over style, accent, pace, and emotion using natural language prompts.

This release supports single and multi-speaker synthesis for applications ranging from short commands to long-form narratives. For more information, see the Gemini TTS documentation page.

Chirp 3: Instant Custom Voice now extends support to ja-JP, now supporting more than 30 locales. For more information, check the Chirp 3: Instant Custom Voice documentation.

We just released three new voice features for Chirp 3: HD Voices. Pace control is available across all locales; pause control is available across all locales; custom pronunciations is available across all locales except bn-in, gu-in, nl-be, sw-ke, th-th, uk-ua, ur-in, and vi-vn. Be sure to check our Chirp 3: HD Voices documentation for more information.

The polyglot voices feature is only supported in multi-regions.

Chirp 3: HD voices with 8 speakers and 31 locales is now GA. It offers real-time streaming and batch processing capabilities and is accessible in global, us, eu, and asia-southeast1 regions.

Explore the latest Chirp 3: HD voices capabilities. Find out their full potential by visiting our updated documentation, specifically the voice controls section.

Chirp 3: HD voices in en-US now support experimental features for pace and pause controls.

Chirp 3: HD voices are only available in the global, us, eu, and asia-southeast1 regions. To use these voices, switch your endpoint to a supported region.

Chirp 3: HD voices now supports 8 new speakers in 31 new locales: ar-XA, bn-IN, cmn-CN, de-DE, en-AU, en-GB, en-IN, en-US, es-ES, es-US, fr-CA, fr-FR, gu-IN, hi-IN, id-ID, it-IT, ja-JP, kn-IN, ko-KR, ml-IN, mr-IN, nl-NL, pl-PL, pt-BR, ru-RU, sw-KE, ta-IN, te-IN, th-TH, tr-TR, and vi-VN.

Journey voices have been rebranded as Chirp HD voices.

Journey Voices now supports the Journey-O speaker for de-de, en-au, en-in, en-gb, es-es, es-us, fr-ca, fr-fr, and it-it.

Cloud TTS Journey voices have been updated to improve the accuracy of generated speech. This means you should notice fewer instances of dropped words.

Journey Voices now supports the de-de, en-gb, en-in, es-us, fr-ca, fr-fr, and it-it locales.

Studio Voices now support synthesis with multiple speakers to generate audios for interviews, interactive storytelling, video games, e-learning platforms, and accessibility solutions.

Journey Voices and streaming synthesis now support the de-de, en-gb, en-in, es-us, fr-ca, fr-fr, and it-it locales.

Cloud Text-to-Speech now offers updated Journey voices with an additional speaker, en-us-Journey-O.

Cloud Text-to-Speech now offers es-ES Studio voices: es-ES-Studio-C and es-ES-Studio-F

Journey voices are now in experimental.

Cloud Text-to-Speech now offers de-DE and fr-FR Studio voices: de-DE-Studio-B, de-DE-Studio-C, fr-FR-Studio-A, and fr-FR-Studio-D.

As of November 13 2023, speaker en-US-Studio-M will no longer be available. All requests sent to en-US-Studio-M will be routed to speaker en-US-Studio-Q. There is no action needed.

Cloud Text-to-Speech now offers en-GB Studio voices: en-GB-Studio-B and en-GB-Studio-C.

Styles are now supported in Neural2 voices through SSML. The following styles are supported

• <google:emotion name="apologetic">
• <google:emotion name="calm">
• <google:emotion name="empathetic">
• <google:emotion name="firm">
• <google:emotion name="lively">

• en-us-Neural2-F
• en-us-Neural2-J

Studio voices now support 5,000 bytes of either text or SSML input per synthesis request.

Feature

Long Audio Synthesis now supports SSML inputs.

Feature

Long Audio Synthesis now supports Studio voices.

The Long Audio Synthesis API now supports the following languages: English, Spanish, French, German, Japanese, Hindi, Italian, Korean, Portuguese, Thai, Vietnamese, Danish, Filipino.

Change

There is no longer billing differentiation for Cloud Text-to-Speech Offline Custom Voice API calls. See the <ReportedUsage> documentation for more details.