Canopy Labs Orpheus TTS (3B)
8 English preset voices (tara, leah, jess, leo, dan, mia, zac, zoe); multilingual research release (7 language pairs) April 2025. Groq deployed two variants on 2026-01-13 (press: $22 per 1M characters, not verified on Groq pricing page).
- Input
- text, audio
- Output
- audio
- License
- apache-2.0
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | canopylabs/orpheus-tts-0.1-finetune-prod | github.com/canopyai/Orpheus-TTS | — |
| Hugging Face | canopylabs/orpheus-3b-0.1-ft | huggingface.co/canopylabs/orpheus-3b-0.1-ft | — |
| Groq | canopylabs/orpheus-v1-english | https://api.groq.com/openai/v1/audio/speech | docs |
| Groq | canopylabs/orpheus-arabic-saudi | https://api.groq.com/openai/v1/audio/speech | — |
| Together AI | — | www.together.ai/models/orpheus-tts | — |
Notable capabilities (1)
- LLM-backbone TTS with emotion tags: Llama-3B-based speech LLM trained on 100k+ h English; tags <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>; ~200 ms streaming latency (~100 ms with input streaming); zero-shot cloning via pretrained model. source