{"slug": "bringing-ode-poetry-to-life-with-mais-audio-models", "title": "Bringing Ode Poetry to life with MAI’s audio models", "summary": "Microsoft AI partnered with poet William Sieghart and creative studio Gravity Road to launch Ode Poetry, a digital experience that uses MAI's audio models to recommend poems based on users' feelings. The system employs MAI-Transcribe for speech understanding and MAI-Voice to replicate Sieghart's vocal style, aiming to scale his one-on-one poetry consultations to a global audience.", "body_md": "#\nBringing Ode Poetry to life with MAI’s audio models\n\nWilliam Sieghart is a world-renowned patron of poetry, a best-selling author of the [“Poetry Pharmacy” anthologies](https://www.penguin.co.uk/books/306569/the-poetry-pharmacy-by-sieghart-william/9781846149542) who helped establish [National Poetry Day](https://forwardartsfoundation.org/national-poetry-day/) in the UK. But it is at his one-on-one “consultations” at events across the country where he brings the power of poetry to life.\n\nDuring these sessions, participants describe what’s on their mind and William recommends a poem. His measured, warm and compassionate approach has resonated with thousands of people for whom he has prescribed poems.\n\nWilliam asked Microsoft AI to help him scale these sessions to a global audience. [Ode Poetry](http://odepoetry.ai/), the result of this collaboration along with creative studio Gravity Road, leverages MAI’s state-of-the-art audio models to deliver a first-of-its-kind digital poetry experience.\n\n“When William approached us with the concept for Ode Poetry, it felt like the perfect opportunity to bring our MAI audio models to life in a way that reflects our humanist-first values,” said Trevor Back, MAI product lead.\n\nOde Poetry asks you questions about how you’re feeling and recommends a poem that might resonate, playing a recording of a real person reading it. AI simply supports the connection between the listener, the creativity of the original poem, and its human reader. It does this through empathetic questions and a thoughtful approach to recommending poems based on William’s literary analysis.\n\nThe project presented an interesting technical challenge. In order to build a voice experience that responds empathetically to users in real time and recommends an appropriate poem, the system must:\n\n- Listen carefully and understand any user\n- Respond at the right time, in the right style\n- Remain grounded in William’s unique style and poetry expertise\n\nWe used MAI’s voice models to power this experience, and worked closely with Ode to build custom solutions for their specific needs, including safety and response quality, all detailed below.\n\n**Speech understanding with MAI-Transcribe**\n\nOde Poetry uses our [MAI-Transcribe model](https://microsoft.ai/models/mai-transcribe-1-5/) to understand spoken language in real time. A leader in its class, it can handle the nuances and complexities of verbal communication, including the many languages, accents, dialects and styles people use today.\n\nThe data reflects this. The latest version of MAI-Transcribe achieves the lowest Word Error Rate (4.86%) of any competitor on the FLEURS benchmark, showcasing its ability to understand many languages and difficult audio examples (such as background noise). The model enables users to engage naturally rather than adapting their speech to the technology. Real-world use cases such as Ode Poetry demonstrate the model’s ability to work effectively in production environments.\n\n## Average Word Error Rate across languages\n\nMean WER on FLEURS dataset across all reported locales per model. Lower is better.\n\n**Bringing expressive speech to conversational AI with MAI-Voice**\n\nOde Poetry also uses [MAI-Voice](https://microsoft.ai/models/mai-voice-2/) to re-create William’s distinctive vocal style. What makes MAI-Voice special is its ability to reproduce William’s speaking style with very high fidelity, using only a short sample of audio. Once you’ve heard William’s voice, you’ll understand why this is so important.\n\nMAI-Voice’s capabilities were achieved by building our own large-scale multilingual data pipeline, augmented with high-fidelity studio recordings of voice talent. This enabled researchers to train a model with both the breadth to sound natural across contexts and the depth to faithfully reproduce any specific speaker. Here’s an example:\n\n*An audio sample showcasing the natural expressivness available with MAI-Voice.*\n\n**Reasoning between conversation and poem recommendations**\n\nOde Poetry is a unique conversational experience because it not only enables a natural conversation, but it also recommends a poem as an outcome, using the structured conditions William has provided for the poems in his “Poetry Pharmacy” books.\n\nWe developed a harness to distill William’s years of experience with personal consultations into a system that can match the unstructured conversation with the user into a framework that enables the right poem to be recommended. This system included carefully chosen deterministic logic and tool-calling mechanisms.\n\nWe also focused on responsible AI for a safe user experience; for example, experimenting with jailbreaks that can trick a language model into attempting real psychiatric diagnoses. Through an iterative approach of safety evals, red teaming, and guardrail updates, we were able to prevent a range of misaligned model behaviors.\n\nHill-climbing was also a critical component to achieving a premium editorial product. High-quality production AI systems hinge on countless small improvements. Accuracy, consistency, latency, reasoning, and expressiveness all contribute to the final result, and a fix in one dimension can cause regressions in another. We evaluated Ode Poetry across a wide range of emotional scenarios and used the results to iteratively refine prompts, recommendation logic and speech output. Achieving a consistently excellent result took relentless iteration of both text and audio prompts, and the shared commitment from both Microsoft AI and William’s team made this collaboration a joint act of creative care.\n\nThis is reflected in the app launching today. As William shared when he first began interacting with his digital extension: “One of [the researchers] recorded my introduction and the next thing I knew, he was playing my voice…and the intonation, the pauses…I just thought, wow, that’s quite nice.\n\n“It’s really exciting for me,” he added, “because what we’re about to embark on together is in a way my lifetime’s ambition, which is to bring poetry to everyone.”\n\nWe invite you to try out the experience of a poetry session with William at [Ode Poetry](http://odepoetry.ai/), and test the latest versions of our models at the [MAI Playground](https://playground.microsoft.ai/).\n\nA view of the Ode Poetry experience. The product features MAI voice models as well as custom harnesses and careful creative direction.\n\n##\nBuild the Future With Us\n\nWe’re a lean, fast-moving lab made up of some of the world’s most talented minds. We have an exciting roadmap of compute at MAI, with our next-generation GB200 cluster now operational. And we have an ambitious mission we truly believe in. We’re also fortunate to partner with incredible product teams giving our models the chance to reach billions of users and create immense positive impact. If you’re a brilliant, highly-ambitious and low ego individual, you’ll fit right in—come and join us as we work on our next generation of models!\n\n[Explore all jobs](/careers/#join-the-team)\n\n##\nRelated Stories\n\n### Introducing MAI-Voice-2\n\n### Introducing MAI-Transcribe-1.5", "url": "https://wpnews.pro/news/bringing-ode-poetry-to-life-with-mais-audio-models", "canonical_source": "https://microsoft.ai/news/ode-poetry-mai/", "published_at": "2026-07-09 17:16:54+00:00", "updated_at": "2026-07-09 17:45:10.385632+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "ai-tools", "natural-language-processing", "ai-infrastructure"], "entities": ["Microsoft AI", "William Sieghart", "Gravity Road", "MAI-Transcribe", "MAI-Voice", "Ode Poetry", "Trevor Back"], "alternates": {"html": "https://wpnews.pro/news/bringing-ode-poetry-to-life-with-mais-audio-models", "markdown": "https://wpnews.pro/news/bringing-ode-poetry-to-life-with-mais-audio-models.md", "text": "https://wpnews.pro/news/bringing-ode-poetry-to-life-with-mais-audio-models.txt", "jsonld": "https://wpnews.pro/news/bringing-ode-poetry-to-life-with-mais-audio-models.jsonld"}}