Releasesby GlyphGradium 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.
Also shipped Jun 10, 2026Gradium in June 2026 →
- [Preview] Launching Flights - agent-native data pipelines in MotherDuck: Build and deploy data pipelines...
- [Preview] Launching Flights - agent-native data pipelines in MotherDuck: Build and deploy data pipelines using a flexible Python runtime, natively connected to your MotherDuck data , for ingest, transformation, warehouse replication, SaaS ETL, and more. Create and manage Flights via SQL, UI, or any MCP-capable AI agent.
Replit | Databricks: Where fast app building meets granular data governance
The Replit and Databricks integration now includes a user-to-machine (U2M) connector, allowing for granular data governance based on Unity Catalog permissions.
Customize Replit Agent with Skills & Custom Instructions
Replit Agent now supports Custom Instructions and Skills, allowing users to define project conventions and guidelines that persist across sessions.
Advisor: Give Any Model a Lifeline to a Smarter One
The new Advisor tool enables smaller, cost-effective models to consult stronger models during generation for improved performance.
Debian 12 reached end of life on 10 June 2026
Debian 12 reached end of life on 10 June 2026. Per our image deprecation policy, this image is available exclusively via the API for the next 30 days before we remove it from our platform.
GitHub CLI 2.94.0
Issue types, sub-issues, and relationships in gh issue This release brings GitHub's advanced issue features to gh issue create , edit , view , and list . You can set and view an issue's type, organize work with sub-issues, and track blocked-by and blocking relationships without leaving the command line: # Set an issue's type gh issue create --type Bug gh...
More from GradiumEvery Gradium release →
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.
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.
A new Gradium Text-to-Speech model is available in public beta
A new Gradium Text-to-Speech model is available in public beta. It handles complex text natively, with no pre-processing or normalization on your side: phone numbers in national and international formats, email addresses, IBAN numbers, time expressions, reference codes, measurements, URLs and ordinals.
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.
- Model selector in Gradium Studio : the Text-to-Speech page now has a Model dropdown to switch between the...
- Model selector in Gradium Studio : the Text-to-Speech page now has a Model dropdown to switch between the production model and gradium-tts-beta , showing each model_name with a copy button. Shareable studio links : pre-configure a session with ?voice= , ?model_name= , ?text= and ?language= and share the full setup as a single link.
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.
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.
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.