Similar tools
Octave TTS is the pioneering large language model (LLM) for text-to-speech, designed to understand and convey the meaning of words rather than just reading them. This advanced system allows users to create any AI voice with a descriptive prompt, guiding its emotional delivery with commands such as "angrier" or "more sarcasm," bringing stories to life with human-like expression. Unlike traditional TTS models, Octave comprehends the context of words, predicting emotions and cadence to generate highly expressive voices.
Octave Voice Design empowers users to create any voice imaginable, from a "sarcastic medieval peasant" to any other unique persona, with a brief prompt or evocative script. In comparative studies, Octave's outputs were preferred over those from ElevenLabs Voice Design, excelling in audio quality, naturalness, and alignment with voice descriptions across diverse prompts.
Octave is the first AI voice generator capable of nuanced acting instructions, interpreting prompts to adjust its voice from "angry" to "just above a whisper." This flexibility allows creators total control over emotional delivery and speaking style, making it ideal for podcasts, voiceovers, audiobooks, and more. Developers can integrate Octave's expressive AI voices into any application via its API.
The Empathic Voice Interface (EVI) 2, a real-time interaction system based on a new voice-to-voice AI model architecture, can converse fluently and adapt to the user's tone of voice. It can emulate a wide range of personalities, accents, and speaking styles, offering flexible prompting and voice modulation tools. EVI 2 is optimized for human well-being, anticipating and aligning with users' preferences through its training for emotional intelligence. Developers are required to adhere to guidelines set by The Hume Initiative, ensuring ethical deployment of empathic AI technology.
Pricing
Octave offers a range of text-to-speech plans:
- Free: $0/month, includes 10,000 characters (~10 minutes), unlimited custom voices.
- Starter: $3/month, includes 30,000 characters (~30 minutes), unlimited custom voices, 20 projects.
- Creator: $10/month, includes 100,000 characters (~100 minutes), $0.20/1,000 additional characters, unlimited custom voices, 1,000 projects.
- Pro: $50/month, includes 500,000 characters (~500 minutes), $0.15/1,000 additional characters, unlimited custom voices, 3,000 projects.
- Scale: $150/month, includes 2,000,000 characters (~2,000 minutes), $0.13/1,000 additional characters, unlimited custom voices, 10,000 projects.
- Business: $900/month, includes 10,000,000 characters (~10,000 minutes), $0.10/1,000 additional characters, unlimited custom voices, 20,000 projects.
- Enterprise: Custom pricing, includes unlimited characters, custom terms, priority support, unlimited custom voices.
EVI & Expression Measurement pricing includes a pay-as-you-go option with $20 in free credit and an enterprise option for high volume and advanced data control requirements.