Blogsby GlyphNov 5
A Closer Look at Phonon
Two weeks after opening up Phonon, the story of the launch: why we built it, what it can do, the demos that came with it, and how it did on Hugging Face's Open TTS Leaderboard.
Gradium Blog the company blog of Gradium: latest posts and feed
Gradium · Company blog · 4.4 a month · 40 posts since Dec 2, 2025
Oct 26
Gradium and Yampa partner on voice AI agents for customer experience
Gradium's voice models now run natively inside Yampa, the agentic platform enterprises use to build, deploy and supervise customer care agents, in SaaS on EU infrastructure or on-premise.
Oct 21
Gradium releases Phonon, an open-source text-to-speech model that runs on any device
Trained on NVIDIA GPUs, Phonon generates natural speech locally in as little as 64.5 MB, on phones, laptops, embedded hardware and in the browser.
Oct 20
Open-Sourcing Phonon: A Suite of Frontier On-Device TTS Models
Today, we're open-sourcing Phonon, now a family of 31m and 40m parameter text-to-speech (TTS) models that set a new standard for naturalness and accuracy on-device.
Oct 19
Gradium is now available on Eden AI
Eden AI is an AI gateway: one API for 500+ models across LLMs, speech, vision and translation, with routing, fallbacks and a dedicated EU endpoint for European data residency.
Oct 7
1,000+ new voices, our most natural set yet
The Gradium voice catalog grows from ~380 to 1.4k voices. The 1,000+ new voices cover 29 accents across English, French, Spanish, German and Portuguese, cast for customer service, narration, ads and characters.
Oct 1
Why we built the fastest robust TTS model
Our latest Text-to-Speech model takes under 50ms for the first audio chunk to arrive. Choosing a fast model does not have to come with cutting corners for model robustness: it improves naturalness and expressivity while retaining our...
Sep 29
Giving voice agents a voice that adapts to context
Most voice agents speak with one preselected voice, whoever is on the line. Once a voice can be created from a text description, the voice becomes another property your code computes from context.
Sep 9
Gradium now available for free on LiveKit Inference
Gradium Text-to-Speech is now available on LiveKit Inference, free until Oct. 9. Gradium TTS is designed for conversational use cases, with voice cloning, low latency (below 250ms TTFA), and robust pronunciation on difficult cases.
Sep 9
How a benchmark change produced a faster TTS model
On June 3, 2026, Gradium's time to first audio on the Coval TTS leaderboard moved from 171.9 ms to 429.6 ms. No model had shipped and no serving infrastructure had changed.
Sep 7
Launching Voice Design: prompt the voice your agent needs
Developers building voice agents ask us for voices matched to the use case in front of them: a Québécoise receptionist for a Montréal dealership, a Paulista support agent for a São Paulo fintech, a narrator in his sixties with the...
Sep 2
Build voice agents with EU and US residency and Zero Data Retention
Two questions come up in almost every enterprise evaluation: where exactly does the inference run, and what do you keep? Data residency pins your Text-to-Speech, Speech-to-Text and Speech-to-Speech sessions to our EU servers, or to our US...
Aug 31
Gradium TTS: you no longer have to choose between latency and accuracy
A new Gradium TTS model is available today, and it is now the default. It reads the cases that break voice agents in production, phone numbers, email addresses, IBANs, with no pre-processing or text normalization on your side.
Aug 19
Gradium voices are now live on AudioStack
AudioStack, the agentic audio production platform for media and advertising, has added Gradium to its roster of voice providers. Our voices are live on the platform now, across multiple languages and regional accents.
Aug 4
New voices: how we pick the one that wins
Picking a voice works like casting: one candidate in a thousand has a hit factor you cannot explain. Here is the methodology behind every flagship voice in the Gradium catalog, from generating hundreds of candidates per category to ranking...
Jul 30
Gradium TTS public beta: open for your hardest cases
A new Gradium TTS model is available today in public beta. It keeps improving on the current production model, handling the complex cases natively, phone numbers, email addresses, IBAN numbers, time expressions and more, with no...
Jul 21
Keyword boosting: teaching Speech-To-Text your vocabulary
Speech-To-Text models rarely see your product's vocabulary, brand names, drugs, athletes, and places, so they fall back on a similar-sounding common word.
Jul 15
Smaller, clearer, better: Phonon Multilingual beats Magpie and NeuTTS Nano in French, German, and Spanish
Phonon, our 100M-parameter on-device Text-To-Speech model, produces up to 3.5x fewer word errors than NVIDIA's Magpie TTS in French, German, and Spanish at 3.6x fewer parameters, and leads NeuTTS Nano on both word error rate and speaker...
Jul 10
Natural conversation, live retrieval: Keenable search with Gradium
Gradium and Keenable are partnering to bring realtime web search into natural voice agents. Gradbot, Gradium's open source voice agent framework, is adding Keenable search so agents can retrieve fresh answers from the live web without...
Jul 8
Gradium Extends Funding to $100 Million and Expands to Silicon Valley
Gradium extends its seed funding to $100 million, welcoming new investors including NVIDIA, and opens a San Francisco Bay Area office to scale its real-time voice AI.
Jul 7
Gradium Powers RMC BFM Drive: AI-Generated Personalized Radio in Renault Vehicles
Gradium powers RMC BFM Drive, the first fully AI-generated, personalized radio experience built into Renault connected vehicles.
Jun 24
Launching Gradium Translate: the best accuracy-latency tradeoff against gemini-3.5-live-translate and gpt-realtime-translate
Gradium launches stt-translate and s2s-translate: real-time Speech-To-Text and Speech-To-Speech translation across English, French, German, Spanish, and Portuguese, with a better accuracy-latency tradeoff than gpt-realtime-translate and...
Jun 10
Gradium TTS, upgraded: more accurate Text-To-Speech
Gradium TTS now runs on a new model: more natural prosody and substantially more accurate pronunciation on the cases that break voice agents in production, including spelling, acronyms, emails, phone numbers, and codes.
Jun 2
Semantic VAD: turn detection that uses meaning, not silence
Acoustic VAD answers "is there a voice right now?" Semantic VAD answers "is the user done talking?" Here's why the distinction decides whether a voice agent cuts users off, how Gradium STT emits multi-horizon turn-completion predictions...
May 26
Phonon update: 1.00% WER on Seed-TTS, smaller than every model we beat
Phonon, our 100M-parameter on-device Text-To-Speech model, reaches 1.00% WER on the Seed-TTS English benchmark, outperforming NeuTTS Air, KaniTTS2, and NeuTTS Nano. With a fixed voice, it drops to 0.83% WER, ahead of Kokoro and Magpie.
About this blog
Gradium's own blog, found on gradium.ai by the daily check; not reviewed yet.
Posts per week, last 26 weeks
4.4 a month over the last six months (or since the feed's oldest post)
Posts by month
Writes about
AI and agents (9), Product and company (9), Reliability and performance (3) in the last six months.
Gradium
Gradium on Companies (companies.fru.dev)Across Glyph:Roundup·Leaders·Paydays·Changefeed·socials·terms
History
Official checkSep 25
not reviewed to official: on gradium.ai