Announcing our seed round. Read more.
Logo

Quora Introduces Audio to Poe with Cartesia

December 10, 2024

“Poe brings together the world's best AI, all in one place. With Cartesia's Sonic model, users can interact with a wide range of high-quality, human-like voices in multiple languages, enhancing their experience on our platform.”

— Spencer Chan, Head of Poe Product, Quora

Quora's mission to share and grow the world's knowledge has inspired the creation of Poe, a versatile chat platform that brings together the best AI models in one place. Poe enables users to engage with latest state-of-the-art LLMs through natural, dynamic conversations, helping transform how people interact with AI.

This week, we launched Sonic on Poe, bringing our text-to-speech technology to the platform's users. With the ability to output audio responses in a wide range of unique voices and languages, users can turn text into audio for a more immersive and entertaining experience.

Poe users can leverage Cartesia Sonic by sending text directly to the bot or by prompting “@Cartesia” followed by the text within any conversation. The message will then be transformed into an audio response in the voice of your choice. This feature allows any Poe user to convert their text-based content on Poe into high-quality audio using one of our 100+ default voices and 14 different languages. Just add --voice [Voice Name] to the end of a message to customize the voice used or to handle different language inputs (e.g. 你好 --voice Chinese Commercial Woman).

Here are 2 examples of how you can use this feature:

1) Nostalgic radio report with 1920's Radioman voice

Ask the Web Search bot for today's top news and listen to it with --voice 1920's radioman

2) Immersive Story with Wizardman voice

Using Grok-beta, generate a short story about a wizard and use --voice Wizardman

This new feature enables Poe users to bring their ideas to life through powerful voice capabilities, including:

  • Realistic Voices: With Cartesia Sonic, Poe provides natural, high-quality audio generation, offering over 100 default voices and support for custom voice creation.
  • Multilingual Support: Featuring diverse accents and support for 14 languages, Poe ensures that content can reach and resonate with a global audience.
  • Advanced Controllability: Creators often seek precise control over how phrases are delivered. Cartesia addresses this need with advanced features like SSML support for break tags and spell tags, as well as IPA support for accurate pronunciation control.
  • Enterprise Scalability: Cartesia is SOC2 compliant and supports unlimited concurrency for its enterprise customers, guaranteeing uptime and performance for high volumes of users.
"We're thrilled to partner with Quora as they build Poe into the central hub for AI interaction. Their platform perfectly embodies our vision of making knowledge more accessible through voice and multimodal AI. We're excited to bring natural speech capabilities to their millions of users and help define how people learn and create with AI."

Karan Goel, CEO, Cartesia