tools
Octave
Octave is Hume's text-to-speech API for expressive speech, custom voices, emotional delivery, and real-time audio streaming.
In inglese
Octave generates expressive speech from text using voice presets, voice cloning, voice design, and natural-language acting instructions. It supports streaming output, multiple audio formats, timestamps, speed control, and multilingual speech.
Developers use it for voiceovers, narration, podcasts, games, accessibility tools, and real-time applications through Hume's API and SDKs. It is a text-to-speech service rather than a general-purpose chat assistant; usage beyond plan limits and enterprise features cost extra.
Features
- Create expressive speech with natural-language acting instructions
- Choose preset voices, clone voices, or design voices from descriptions
- Stream audio output with approximately 300 ms time to first byte
- Generate speech in 16+ languages with native-quality accents
- Export MP3, WAV, OGG, FLAC, or raw PCM audio
- Return word- and phoneme-level timestamps for captions and lip sync
- Adjust speaking speed from 0.25x to 4x
- SDK support for Python, TypeScript, .NET, and Swift
Use cases
- Create voiceovers for training, marketing, and product videos
- Narrate stories, audiobooks, and podcasts
- Build real-time voice interfaces and interactive applications
- Localize content into multiple languages and accents
- Generate character voices for games and interactive media
- Synchronize generated speech with captions, animation, or lip movements
Pros
Cons
Latest updates
- Octave 2: next-generation multilingual voice AI (Octave 2)
Launching Octave 2 for text-to-speech in 11 languages and EVI 4 mini for the speech-to-speech API.
Capabilities
- Text to speech — “Generate expressive, natural-sounding speech that conveys the full range of human emotion.” source
- Voice cloning — “Choose from a curated library of expressive voices, clone any voice from a sample, or design entirely new voices from natural language descriptions.” source
- Many languages — “Native-quality speech in 16+ languages with authentic accents.” source
- API — “Octave is Hume's text-to-speech API with emotional intelligence.” source
Get it
Pricing
- Starting price
- $3/mo
- Prices checked
- 2026-09-25
Free
Free
- 10,000 monthly included characters
- 5 minutes of monthly EVI usage included
- 15 requests per minute
- 1 concurrent connection
- Unlimited voice cloning (create and use)
Starter
- $3 / month
- 30,000 monthly included characters
- 40 minutes of monthly EVI usage included
- 5 concurrent connections
- Unlimited voice cloning (create and use)
Creator
- $14 / month
- 140,000 monthly included characters
- 200 minutes of monthly EVI usage included
- 75 requests per minute
- 5 concurrent connections
- Unlimited voice cloning (create and use)
Pro
- $70 / month
- 1,000,000 monthly included characters
- 1,200 minutes of monthly EVI usage included
- 10 concurrent connections
- Unlimited voice cloning (create and use)
Scale
- $200 / month
- 3,300,000 monthly included characters
- 5,000 minutes of monthly EVI usage included
- 20 concurrent connections
- 3 team seats
- Unlimited voice cloning (create and use)
Business
- $500 / month
- 10,000,000 monthly included characters
- 12,500 minutes of monthly EVI usage included
- 30 concurrent connections
- 5 team seats
- Unlimited voice cloning (create and use)
Enterprise
Price on request
- As much text-to-speech usage as you need
- As much EVI usage as you need
- As many concurrent connections as you need
- Unlimited team seats
- Unlimited voice cloning (create, use and access via API)
- Slack support