Canopylabs · Speech
Orpheus V1 English
CanopylabsSpeechcanopylabs/orpheus-v1-english familyOne of its sources says the weights aren't publicly available.
Canopy Labs' expressive English text-to-speech model with six voices and bracketed vocal directions such as [cheerful] or [whisper]. Generates WAV audio via the /v1/audio/speech endpoint; input is limited to 200 characters per request.
- Market median price
- $22.00 /1M chars
- Max context
- 4K
- Listings
- 4
- Providers
- 3
Evidence and sources
Sources: Groq API data, LLMGateway data, LiteLLM data, Models.dev dataPrimary data from Groq API
from LLMGateway: name, description
from LiteLLM: variant
from Models.dev: weights availability
Input & output
as stated by the model's providersText
Audio
Also known as: canopylabs/orpheus-v1-english, groq/canopylabs/orpheus-v1-english
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works