@GradiumAI

The voice layer for agents. Real-time, accurate, natural voice APIs: TTS, STT, turn-taking & voice design. Devs: build → https://xitter.cf/t.co/BMTX2dOALw

gradium.ai
Joined September 2025
  • Tweets289
  • Following38
  • Followers5.5K
125Media
A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. gradium.ai/phonon🧵
151
268
147
2,081
316,371
Gradium retweeted
Loci
@askloci10h
Loci now runs Phonon as the default TTS engine on mobile. Try it out today at our link in bio
Gradium
@GradiumAIOct 20
A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. gradium.ai/phonon🧵
1
3
8
408
Gradium retweeted
Godefroy
@Godefroy18h
Gradium just released Phonon, an open weights TTS model small enough for a CPU. Micdrop now runs it inside your Node voice agent, with no API key, no GPU and no audio leaving the machine. First words in under 100 ms. Five languages, 102 voices 👇 micdrop.dev/docs/ai-integrat…

Phonon TTS in Node.js | Micdrop

Run Gradium's Phonon text to speech in your Node voice agent, in English, French, German, Spanish and Portuguese, with 102 voices and its first audio in under 100 ms.

micdrop.dev
Gradium
@GradiumAIOct 20
A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. gradium.ai/phonon🧵
1
1
7
271
Gradium retweeted
Godefroy
@Godefroy18h
Replying to @GradiumAI
Congrats on the launch, Gradium team! 🎉 We shipped the Micdrop integration today, so Phonon now runs inside a Node voice agent, on the CPU, with no API key. First audio in 30 to 100 ms on a single M2 core, incredible! micdrop.dev/docs/ai-integrat…

Phonon TTS in Node.js | Micdrop

Run Gradium's Phonon text to speech in your Node voice agent, in English, French, German, Spanish and Portuguese, with 102 voices and its first audio in under 100 ms.

micdrop.dev
1
2
113
Phonon is now the default voice in Nativ. Nativ is the free, open-source app from @Prince_Canuma and the Neywa Labs team for running AI models locally, built on MLX-Audio.
Gradium
@GradiumAIOct 20
A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. gradium.ai/phonon🧵
3
5
22
1,163
Gradium retweeted
Marc Sun@_marcsun21h
🤗 transformers serve now speaks 🔊 We just added an OpenAI-compatible `/v1/audio/speech` endpoint. And we couldn't have picked a better model to launch it with than Phonon, @GradiumAI brand-new on-device TTS: tiny, fast and multilingual. Run with: transformers serve gradium/phonon-40m-en
2
7
21
560
On-device voice agents are ready to ship with Phonon and @pipecat_ai. Pipecat runs inside the IOS app and directs the conversation, deciding who speaks and when. Phonon 31m gives each character its own voice and drives the lip sync on their animated faces. github.com/pipecat-ai/ios-li…
Gradium
@GradiumAIOct 20
A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. gradium.ai/phonon🧵
3
2
51
2,282
I told you it was not finished! Banger release from the goated french speech team, aka @GradiumAI day0 transformers 🤗 support, have fun building with it!
Gradium
@GradiumAIOct 20
A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. gradium.ai/phonon🧵
2
5
20
859
Yesterday we open-sourced Phonon, and today we’re at NVIDIA GTC Berlin. Phonon’s inference stack includes an NVIDIA CUDA backend, so it runs on professional and gaming GPUs and on embedded hardware with Jetson. Today we’re announcing it with @nvidia: gradium.ai/blog/gradium-rele…

Gradium releases Phonon, open-source on-device Text-to-Speech

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.

gradium.ai
Gradium
@GradiumAIOct 20
A new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. gradium.ai/phonon🧵
2
4
47
1,789

Gradium open-sources Phonon, on-device text-to-speech models

Article · @voiceaispace
1
4
10
480
And if you want to scale even smaller than Phonon, @Manu__Orsini leads the way towards building the smallest possible TTS models that stay accurate and natural.
kyutai@kyutai_labsOct 20
Pocket TTS has been getting updates those last few days. While it was ~100M parameters, we release smaller versions, down to 1.9M: an 18.2M model with the quality of the original, a 6.9M model, and a 1.9M model that runs 103x faster than real time on one CPU core. All with voice cloning.
1
3
26
1,576
@appningbyforvia is a design partner using Phonon in joint R&D in an automotive context. @FORVIA
3
1
13
2,551
@autonomous_labs is a hardware partner using Phonon to give their personal open-source OS robot a voice generated on the robot itself. @dee_hw
1
189
This is the beginning of a new open-source arc for us, stay tuned for the next release!
19
2,351
Load more