{"slug": "gradium-is-now-available-on-eden-ai", "title": "Gradium is now available on Eden AI", "summary": "Eden AI has added Paris-based Gradium's Text-to-Speech, Speech-to-Text and speech translation to its AI gateway, which offers one API for 500+ models, with Gradium calls pinned to Eden AI's EU endpoint so audio is processed in Europe by a European company. Gradium runs as a passthrough rather than through Eden AI's shared schema because its TTS reaches first audio in 50ms and the normalization layer would add latency in the same order of magnitude as the model itself. Developers call Text-to-Speech by setting model to audio/tts/gradium on Eden AI's universal-ai endpoint, while Speech-to-Text and speech translation run as async jobs on audio/speech_to_text_async/gradium and audio/speech_to_text_async/gradium/stt-translate, with live streaming transcription requiring Gradium's API directly.", "body_md": "# Gradium is now available on Eden AI\n\nEden 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. Gradium's Text-to-Speech, Speech-to-Text and speech translation are now [available through that API](https://www.edenai.co/providers/gradium).\n\nA voice recording identifies the speaker and, in support, healthcare or banking calls, often carries personal data. Teams building voice products have to know where that audio is processed and which company processes it.\n\n## A European voice stack on Eden AI's EU endpoint\n\nEden AI customers asked for European voice options. Until now, Text-to-Speech on Eden AI came from US providers, which left teams that want voice data processed in Europe, by a European company, with no choice.\n\nGradium is built in Paris, and Eden AI calls to Gradium are pinned to the EU region, so teams get Gradium's voice quality and European data residency through the API key they already use.\n\n## Why Gradium runs as a passthrough on Eden AI\n\nEden AI maps most providers to a shared schema: one request shape, one response shape, and switching providers means changing one string. That mapping adds a few milliseconds per call. Batch transcription absorbs them, but less so in a real-time voice agent.\n\nGradium's TTS reaches first audio in **50ms**, so a normalization layer would add latency in the same order of magnitude as the model itself.\n\nGradium therefore runs as a passthrough on Eden AI. You keep the single key, the single bill and the rest of the catalogue, and Text-to-Speech returns audio in the same request.\n\n## How to call Gradium TTS, STT and translation through Eden AI\n\n``` python\nimport requests\n\nresponse = requests.post(\n    \"https://api.edenai.run/v3/universal-ai\",\n    headers={\"Authorization\": \"Bearer YOUR_EDENAI_API_KEY\"},\n    json={\n        \"model\": \"audio/tts/gradium\",\n        \"input\": {\"text\": \"Bonjour, comment puis-je vous aider ?\"},\n    },\n)\n```\n\nSpeech-to-Text and speech translation use the same shape on `audio/speech_to_text_async/gradium` and `audio/speech_to_text_async/gradium/stt-translate`. On Eden AI, these two run as async jobs, suited to recorded audio. For live streaming transcription, call the [Gradium API](https://docs.gradium.ai/guides/introduction) directly.\n\n## Get started\n\nWith Gradium on Eden AI's EU endpoint, the audio is processed in Europe by a European company. To try it, grab an Eden AI key and set `model` to `audio/tts/gradium`.\n\n- Gradium on Eden AI: [edenai.co/providers/gradium](https://www.edenai.co/providers/gradium)\n- Eden AI documentation: [docs.edenai.co](https://docs.edenai.co)\n- Gradium documentation: [docs.gradium.ai](https://docs.gradium.ai/guides/introduction)\n- Questions or volume pricing: [talk to us](https://gradium.ai/contact?subject=Sales)\n\n## Frequently Asked Questions\n\nPost to https://api.edenai.run/v3/universal-ai with your Eden AI key and set model to audio/tts/gradium for Text-to-Speech. Speech-to-Text and speech translation use the same shape on audio/speech_to_text_async/gradium and audio/speech_to_text_async/gradium/stt-translate.\n\nIn Europe. Eden AI calls to Gradium are pinned to the EU region, and Gradium is a European company built in Paris, so the audio is processed in Europe by a European company.\n\nEden AI maps most providers to a shared schema, which adds a few milliseconds per call. Gradium's TTS reaches first audio in 50ms, so a normalization layer would add latency in the same order of magnitude as the model itself. As a passthrough, you keep the single key, the single bill and the rest of the catalogue, and Text-to-Speech returns audio in the same request.\n\nOn Eden AI, Speech-to-Text and speech translation run as async jobs, suited to recorded audio. For live streaming transcription, call the Gradium API directly.", "url": "https://wpnews.pro/news/gradium-is-now-available-on-eden-ai", "canonical_source": "https://gradium.ai/blog/eden-ai-gradium-partnership", "published_at": "2026-10-19 00:00:00+00:00", "updated_at": "2026-10-20 17:48:09.919589+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "artificial-intelligence"], "entities": ["Eden AI", "Gradium", "Paris"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/gradium-is-now-available-on-eden-ai", "markdown": "https://wpnews.pro/news/gradium-is-now-available-on-eden-ai.md", "text": "https://wpnews.pro/news/gradium-is-now-available-on-eden-ai.txt", "jsonld": "https://wpnews.pro/news/gradium-is-now-available-on-eden-ai.jsonld"}}