D
Orpheus 3B
Orpheus 3B, a text-to-speech model from DeepInfra.
speechModelOverride: { model: "orpheus-3b-deepinfra" }
Canopy Labs·served via
DeepInfra·Released March 2025Pricing
- Per 1M characters
- $7.00
- Per 1M characters
- $0
Specifications
- Context window
- 10,000 tokens
- Released
- March 2025
- Model string
- canopylabs/orpheus-3b-0.1-ft
- Capabilities
- Open source
Parameters
Model options, passed in
speechModelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
voiceVoice to use in TTS. | Select | tara | taraleahjessleodanmia+1 |
speedSpeaking speed. 1.0 is normal. | Number | 1 | 0.5–2, step 0.05 |
response_format | Select | mp3 | mp3wavflacopus |
Voices · 7
Use this model
await mindstudio.textToSpeech({ text: "...", speechModelOverride: { model: "orpheus-3b-deepinfra", config: { voice: "tara", speed: 1, }, }, });