Gradium Release notes from Gradium

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.

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.

Gradium has completed its SOC 2 Type II attestation

The voice catalog grows from about 390 to more than 1,400 voices

Gradium expanded its voice catalog to over 1,400 voices and added features for preview samples, usage exports, and pronunciation dictionary management.

Gradium has achieved ISO 27001 certification, independently audited by A-LIGN

Gradium has achieved ISO 27001 certification, independently audited by A-LIGN. Visit our Trust Center for certification details and security documentation .

Create a voice from a written description, no audio sample needed

Create a voice from a written description, no audio sample needed. Describe the accent, age and character you need, generate up to five candidates, and keep your favourite. The voice works with the same Text-to-Speech endpoint as any catalogue voice. In our blind listening evaluation, native speakers judged how well voices matched accent prompts.

A session can last up to 3000 seconds

A new Gradium Text-to-Speech model is live and is now the default

A new Gradium Text-to-Speech model is live and is now the default. Existing voices, including custom voices, work as-is. The model reads the structured entities that break voice agents in production, such as phone numbers, email addresses, IBANs and reference codes, with no pre-processing or text normalization needed.

Speech-to-Text requests now require a language in json_config

Speech-to-Text requests now require a language in json_config . Our ASR gives its best results when the language is known, so set it whenever you can: en , fr , es , pt , or de . When the language is not known ahead of time, pass any and the model detects it from the audio. Requests that already set a language or any are unaffected.

2026.02

We're excited to announce major updates to the Gradium API and Gradium Studio, delivering enhanced text-to-speech (TTS) and speech-to-text (STT) capabilities for developers and enterprises.

Our live translation models ( stt-translate for translated transcription and s2s-translate for...

Our live translation models ( stt-translate for translated transcription and s2s-translate for Speech-to-Speech) now produce more natural, more accurate translations, with better context understanding across a conversation. The quality gains are most noticeable on conversational speech. See Speech-to-Speech and the Speech-to-Text overview to get started.

A new Speech-to-Text model is now live on the standard endpoint

A new Speech-to-Text model is now live on the standard endpoint. Transcription is more robust on low volume audio, so soft speakers and far field microphones are recognised with improved reliability. Endpointing is more reactive, so the end of an utterance is detected sooner and voice agents can start responding with less delay.

Get the vocabulary specific to your product transcribed correctly: brand and product names, people, places...

Get the vocabulary specific to your product transcribed correctly: brand and product names, people, places, drugs, and jargon. Pass a dictionary of the terms you care about in your STT json_config , and the model gives them priority while decoding, in real time, with no retraining.

Gradium TTS now runs on an upgraded default model focused on more expressive speech and better reliable...

Gradium TTS now runs on an upgraded default model focused on more expressive speech and better reliable pronunciation for production voice agents. Improved natural prosody, phrasing, intonation, and pacing. This is especially noticeable in conversational turns and longer passages.