Octave - Text-to-Speech with Emotional Intelligence | Hume AI
Octave
Text-to-speech with emotional intelligence. Generate expressive, natural-sounding speech that conveys the full range of human emotion.
Text-to-speech
Narrate a Story
Conversational
62/500
Language
English
Voice
Mysterious Woman
Play audio
Type text and click play to hear it spoken
Your voice, your way
Choose from a curated library of expressive voices, clone any voice from a sample, or design entirely new voices from natural language descriptions. Create the perfect voice for your brand.
Vince Douglas
The speaker has a reflective, Black American voice, reminiscent of a Harlem storyteller sharing nostalgic memories with a tone of resilience and quiet strength.
Mysterious Woman
A smooth, breathy, rich, resonant, and elegantly poised voice, conveying authority with a captivating warmth and sophisticated precision.
Male English Actor
The speaker has a confident, charismatic tone, like a tech guru explaining a new technology with infectious enthusiasm, and the excitement of a viral storyteller.
Inspiring Woman
An inspiring female voice with a soft, welcoming, prophetic tone.
Campfire Narrator
Previously Texan Narrator. The best, most amazing and famous audiobook narrator ever, with the richest and warmest and most inviting voice.
TikTok Fashion Influencer
Tiktok fashion influencer with deep, rich, soothing voice.
Colton Rivers
Previously Charming Cowboy. A grizzled old cowboy with a folksy Texan drawl Southern accent, speaking in a charismatic tone with a deep but relaxed vibe.
Inspiring Man
An inspiring male voice with a soft, welcoming, prophetic tone.
Terrence Bentley
A middle-aged African American man, reminiscing with a slightly gravelly voice and a tone of hard-earned wisdom.
Alice Bennett
A sophisticated British female narrator with a gentle, warm voice, recounting the ending of a classic romance novel.
Sitcom Girl
The star of a popular sitcom, with frequent inner monologues about her life.
Unserious Movie Trailer Narrator
An American, deep middle-aged male film trailer narrator for a film about chickens.
Big Dicky
The speaker has a booming, charismatic radio voice, like a Texan fishing guru with a hint of gravel and an infectious laugh, perfect for reeling in listeners to "Big Dicky's live fishing frenzy."
English Children's Book Narrator
British Children's Storybook Narrator with a deep, rich, amazing, warm, inviting voice.
Spanish Instructor
The speaker has a Mexican accent.
Fastidious Robo-Butler
The speaker is a fussy yet ultimately kindhearted droid with a precise received pronunciation accent and a slightly nasal tone.
Ito
A male adult voice made famous by EVI 1 and 2
Kora
A female adult voice made famous by EVI 1 and 2
Acting instructions
Direct the emotional delivery of every line. Specify tone, pacing, emphasis, and mood with natural language instructions. From whispered secrets to excited announcements—Octave performs exactly as directed.
“With warm enthusiasm”
Play“Speak slowly and in a whisper”
Play“Speak with a sarcastic tone”
Play
Real-time streaming
Start playback in milliseconds with streaming audio output. Octave begins generating speech instantly, streaming audio chunks as they're ready. Perfect for real-time applications where every millisecond counts.
~300ms
Time to first byte
Features
Everything you need for text-to-speech
Multilingual
Native-quality speech in 16+ languages with authentic accents.
Word and phoneme level timestamps
Precise timing data for lip sync, captions, and highlighting.
Multiple formats
Export as MP3, WAV, OGG, FLAC, or raw PCM audio.
Contextual continuation
Natural flow across requests with smart heteronym disambiguation.
Streaming output
Start playback immediately with chunked audio delivery.
Speed control
Adjust speaking rate from 0.25x to 4x speed.
Audio normalization
Consistent volume levels across all generated audio.
Voice presets
Save and reuse voice configurations for consistency.
For Developers
Generate speech in seconds
Integrate Octave into your application with just a few lines of code. Full SDK support for Python, TypeScript, .NET, Swift, and more.
TypeScript
Python
.NET
Swift
import { HumeClient } from 'hume'
const client = new HumeClient({ apiKey: 'YOUR_API_KEY' })
await client.tts.synthesizeFileStreaming({
utterances: [
{
text: 'Dogs became domesticated between 23,000 and 30,000 years ago.',
voice: { name: 'Male English Actor', provider: 'HUME_AI' },
},
],
})
Case Studies
Niantic Spatial × Hume AI
Creating Interactive & Spatially Aware AI Companions
In partnership with Snap Inc. (hardware) and Hume AI (voice), Niantic Spatial has developed location-aware companions for Spectacles, blending Snap Inc.’s AR glasses, Niantic Spatial’s Large Geospatial Model, and Hume’s Empathic Voice Interface (EVI) for natural, emotionally intelligent conversation.
GAF Powers Professional Training with Hume’s Text-to-Speech
To support their extensive training programs and marketing initiatives, GAF leverages Hume's text-to-speech technology to make internal training videos and marketing voiceovers.
Hume AI powers conversational learning with Coconote
While traditional note-taking apps require students to manually scroll and search through content, Coconote is creating interactive study experiences through conversational AI.
Enterprise Ready
Built for business.
SOC 2 Type II
Enterprise-grade security with industry-leading practices.
HIPAA compliant
Build healthcare applications with confidence.
Enterprise plans
Custom SLAs, dedicated support, and volume pricing.
FAQ
What is Octave?
Octave is Hume's text-to-speech API with emotional intelligence. It generates expressive, natural-sounding speech that can convey the full range of human emotion, going beyond flat robotic voices to deliver truly lifelike audio.