# Gradium — Giving voice agents a voice that adapts to context

- Company: Gradium (gradium.ai)
- Announced: 2026-09-29
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://gradium.ai/blog/voice-that-adapts-to-context
- Record: https://forck.live/items/18301-giving-voice-agents-a-voice-that-adapts-to-context
- Subject: Gradium TTS / Phonon

Gradium introduced Voice Design, which creates natural, realistic voices from a text description (prompt) rather than from presets or audio samples. Voice characteristics become output computed from the same context the agent uses to decide what to say. The post builds an end-to-end pipeline combining Voice Design with a decision model (Jev from TypeSafe AI) for context extraction and Gradium TTS for speech synthesis.

## Evidence

Verbatim from https://gradium.ai/blog/voice-that-adapts-to-context:

> With Voice Design , you can now create natural, realistic voices from a text description (or "prompt"). Voice characteristics become output your code computes, from the same context it already uses to decide what the agent says.

---

Record: https://forck.live/items/18301-giving-voice-agents-a-voice-that-adapts-to-context
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md