Capabilities
Explore what Octave 1 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Hume AI
- Product
- Text-to-Speech
- Release Date
- Feb 26, 2025
- Data Policy
- Not specified
- Region
- Global
- Input
- Text
- Output
- Audio
Playground
Try Octave 1 by Hume AI. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Octave 1.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Hume AI | Not specified | Audio | $85.00 / 1M characters | — | hume/octave-1:hume |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 5000 |
| Formats | mp3, wav, pcm |
Provider Notes
hume/octave is Hume's mutable automatic selector, hume/octave-1 is the stable exact version, and hume/octave-2 is preview. The mutable and preview entries require exact selection. HTTP supports file, JSON, streamed-file, and newline-delimited streamed-JSON synthesis; the speech WebSocket supports Hume's bidirectional input stream. Voice IDs are provider-neutral by default so Hume can resolve Voice Library or custom IDs; set voice_provider only to explicitly scope an ID. String voice names default to HUME_AI, while custom names require CUSTOM_VOICE. Octave 1 supports English/Spanish, acting instructions, and voice design. Octave 2 supports 11 languages, requires a voice, and adds word/phoneme timestamps, but does not yet support acting instructions.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hume/octave-1",
"input": "Make every word count.",
"voice": "Colton Rivers",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | hume/octave-1 — Required model identifier. |
transport | View Accepted Values |
version | View Accepted Values |
voice_provider | View Accepted Values |
context | View Accepted Values |
include_timestamp_types | View Accepted Values |
num_generations | View Accepted Values |
split_utterances | View Accepted Values |
strip_headers | View Accepted Values |
temperature | View Accepted Values |
instant_mode | View Accepted Values |
trailing_silence | View Accepted Values |
context_generation_id (WebSocket) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 5000 |
| Formats | mp3, wav, pcm |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Octave 2Hume AI | Not specified | $42.50 / 1M characters | — |
| Octave (Auto)Hume AI | Not specified | $85.00 / 1M characters | — |
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| tts-rt-v2Soniox | Not specified | $11.985 / 1M characters | — |
| Inworld TTS-2 FlashInworld AI | Not specified | $12.75 / 1M characters | — |
