Releasesby GlyphThe default text-to-speech model in the API and Studio now handles break durations more accurately and...
The default text-to-speech model in the API and Studio now handles break durations more accurately and improves number pronunciation in Spanish and Portuguese.
Also shipped Nov 9, 2026Gradium in November 2026 →
The following AlloyDB AI features and improvements are generally available ( GA ): - Smart batching for AI...
The following AlloyDB AI features and improvements are generally available ( GA ): Smart batching for AI functions: AI function acceleration is generally available for ai.if , ai.rank , ai.analyze_sentiment , ai.summarize , ai.extract , ai.classify , and ai.generate on AlloyDB clusters running PostgreSQL 17 and later.
To support your FinOps practices, you can now opt in to compute cost attribution in BigQuery editions
To support your FinOps practices, you can now opt in to compute cost attribution in BigQuery editions. This feature attributes billed compute charges directly to the query projects that use your administration project's reservation capacity.
Query performance troubleshooting and job and system performance comparison in the BigQuery jobs explorer are...
Query performance troubleshooting and job and system performance comparison in the BigQuery jobs explorer are generally available (GA). For more information, see Troubleshoot job performance and Diagnose performance regressions by comparing jobs and systems .
When you create or schedule a pipeline, you can specify the maximum number of concurrently executed pipeline...
When you create or schedule a pipeline, you can specify the maximum number of concurrently executed pipeline tasks. This feature is generally available (GA).
You can use compression functions in GoogleSQL to compress or decompress bytes or string values by using the...
You can use compression functions in GoogleSQL to compress or decompress bytes or string values by using the Zstandard (Zstd) lossless data compression algorithm. The following functions are supported: ZSTD_COMPRESS ZSTD_DECOMPRESS_TO_BYTES ZSTD_DECOMPRESS_TO_STRING These functions are in Preview .
Fast mode for Anthropic Claude models is generally available
Fast mode for supported Anthropic Claude models, starting with Claude Fable 5.2 ( claude-fable-5-2 ), is available in General Availability (GA) . You can set "speed": "fast" in online pay-as-you-go prediction requests to accelerate output token generation for latency-sensitive agentic workflows.
More from GradiumEvery Gradium release →
Gradium adds data residency configuration in Studio
Gradium updated Studio to allow admins on paid plans to configure data residency settings under Organization controls.
A new speech-to-text model is now in production, with better transcription accuracy and end-of-turn detection
A new speech-to-text model is now in production, with better transcription accuracy and end-of-turn detection. It replaces the previous model in place, so you don't need to change your requests. See Speech-to-Text .
TTS output in resampled formats now starts without the extra 40 ms of silence
Gradium updated its TTS output to remove 40 ms of silence at the start of resampled audio chunks. Developers should now use start_s and stop_s parameters instead of assuming fixed chunk sizes.
New voice clones are now enhanced by default
Gradium voice clones are now enhanced by default, with an option to opt out via the API.
You can now filter GET /voices/ by locale , gender and use_case , including combinations of these filters
The GET /voices/ endpoint now supports filtering by locale, gender, and use case. Additionally, voice responses now include a rank field to help prioritize custom and catalog voices.
Phonon brings text-to-speech to local devices, including phones, laptops, embedded devices and browsers
Phonon brings text-to-speech to local devices, including phones, laptops, embedded devices and browsers. Run speech generation locally for applications that need offline operation or want to keep inference on the device. Use voices from the catalog, or custom voices created through Gradium, in your local applications.
Organization page with role-based access controls
Gradium updated the organization page with new role-based access controls, improved invitation management, and data residency visibility.
The Voice localizer is now in Studio, out of beta
The Voice localizer is now in Studio, out of beta. Pick a voice, describe the accent you want, and compare three takes at different strengths. The one you keep is saved as a new custom voice. You can also start from Localize in any voice's menu in the catalog. See the Voice Localization guide .