tools
Octave
Octave is Hume's text-to-speech API for expressive speech, custom voices, emotional delivery, and real-time audio streaming.
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
Pricing
- Starting price
- $3 / month
- Pricing checked
- 2026-09-19
Free
$0 / month
- 10,000 monthly included characters
- 15 requests per minute
- 5 minutes of monthly EVI usage
- Unlimited voice cloning
Starter
$3 / month
- 30,000 monthly included characters
- 15 requests per minute
- 40 minutes of monthly EVI usage
- Unlimited voice cloning
Creator
$7 / month
- 1st month 50% off; regular price $14 / month
- 140,000 monthly included characters
- $0.15/1,000 additional characters
- 75 requests per minute
- Unlimited voice cloning
Pro
$70 / month
- 1,000,000 monthly included characters
- $0.12/1,000 additional characters
- 75 requests per minute
- 1,200 minutes of monthly EVI usage
- 10 concurrent connections
Scale
$200 / month
- 3,300,000 monthly included characters
- $0.10/1,000 additional characters
- 150 requests per minute
- 5,000 minutes of monthly EVI usage
- 20 concurrent connections
- 3 team seats
Business
$500 / month
- 10,000,000 monthly included characters
- $0.05/1,000 additional characters
- 225 requests per minute
- 12,500 minutes of monthly EVI usage
- 30 concurrent connections
- 5 team seats