Gradium
Gr
PricingBlog
Sign in
Sign in

Spotlight post

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.

July 8, 20263 min read
Gradium Extends Funding to $100 Million and Expands to Silicon Valley

Models

Text-to-SpeechTurn text into natural sounding voiceSpeech-to-TextTranscribe audio into text instantlyLive TranslationConvert voice to voice in real timeVoice CloningInstance or pro voice cloneOn-Device TTSOffline real-time natural voice

Showcase

Agent DemoTest our voice agent liveGradbotBuild voice agents in a single promptApp GalleryApps built on Gradium

Latest post

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 similarity. It clones a reference voice across five languages: English, French, German, Spanish, and Portuguese.

July 15, 20265 min read
Smaller, clearer, better: Phonon Multilingual beats Magpie and NeuTTS Nano in French, German, and Spanish

Build

DocsStart building in minutesStatusMonitor system performanceTrustSecurity and compliance

Company

AboutMeet the team behind GradiumCareersCome build with usPressMedia and news resources
PricingBlog
Sign in

Spotlight post

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.

July 8, 20263 min read
Gradium Extends Funding to $100 Million and Expands to Silicon Valley

Models

Text-to-SpeechTurn text into natural sounding voiceSpeech-to-TextTranscribe audio into text instantlyLive TranslationConvert voice to voice in real timeVoice CloningInstance or pro voice cloneOn-Device TTSOffline real-time natural voice

Showcase

Agent DemoTest our voice agent liveGradbotBuild voice agents in a single promptApp GalleryApps built on Gradium

Latest post

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 similarity. It clones a reference voice across five languages: English, French, German, Spanish, and Portuguese.

July 15, 20265 min read
Smaller, clearer, better: Phonon Multilingual beats Magpie and NeuTTS Nano in French, German, and Spanish

Build

DocsStart building in minutesStatusMonitor system performanceTrustSecurity and compliance

Company

AboutMeet the team behind GradiumCareersCome build with usPressMedia and news resources

Models

Text-to-SpeechSpeech-to-TextSpeech-to-SpeechLive translationOn-DeviceVoice Cloning

Showcase

Agent DemoGradbotApp Gallery

Build

PricingDocsStatusTrust

Company

AboutBlogCareersPressContact

Socials

XGitHubLinkedInDiscord
Gradium

© 2026 Gradium. All rights reserved.

Terms of ServicePrivacy Policy
Open Source Voice Agent Framework

Vibecode abank agentinminutes

50 lines of code. Any OpenAI-compatible LLM. VAD, turn-taking, fillers, interruptions, and low latency handled for you.

Fork MeRead Blog →
Live Demos

Prototype
with Gradbot

Each demo runs a live voice AI agent built with Gradbot. Click to start, then speak naturally.

All templatesBrowse the gallery →
Click to launch demo
Developer Experience

50 lines to your first agent

Gradbot gives you the event loop for voice agents.
You write the logic, it handles the rest.

main.py
python
import gradbot

voice = gradbot.flagship_voice("Emma")
config = gradbot.SessionConfig(
    voice_id=voice.voice_id,
    instructions="You are a helpful assistant.",
    language=voice.language,
)

input_handle, output_handle = await gradbot.run(
    session_config=config,
    input_format=gradbot.AudioFormat.OggOpus,
    output_format=gradbot.AudioFormat.OggOpus,
)
  • 1
    Unified Intelligence: STT, LLM, and TTS coordinated into one seamless loop.
  • 2
    Bi-directional audio streaming with precision VAD and silence detection.
  • 3
    Live transcription, captions generation, and tool calls handled in the same cycle.
  • 4
    Seamless turn-taking, natural fillers, and barge-in handled automatically.
  • 5
    Unlimited voices via instant or pro cloning on any OpenAI-compatible model.
Fork Me

Ready to build?

Gradbot is built for prototyping. For production, use Gradium APIs
with mature agent integrations like LiveKit and Pipecat.

GitHubDocs →Discord →