- Home
- Text-to-speech tools
- Orpheus TTS
On the recordRead 13 Oct 202624 facts
Orpheus TTS
Orpheus TTS · San Francisco, California, United States
On the record
- API access
- Yesgithub.com · read 20 Sep 2026
- Baseten deployment
- The Baseten model page lists text input, audio output, Apache 2.0 licensing, and H100 MIG 40GB hardware.baseten.co · read 12 Oct 2026
- Baseten throughput
- The Baseten model page says its implementation supports 16 concurrent real-time streams with variable traffic, 24 with consistent traffic, or 128 concurrent non-real-time generations.baseten.co · read 12 Oct 2026
- Commercial use
- Yesgithub.com · read 20 Sep 2026
- Company focus
- Canopy Labs describes itself as building realtime interactive models for avatars.canopylabs.ai · read 13 Oct 2026
- Current hosted offering
- The maker’s Orpheus page describes enterprise deployments on customer infrastructure, including on-premise or private cloud, with priority support and SLA guarantees.orpheus.canopylabs.ai · read 13 Oct 2026
- Customization
- The README provides data-processing scripts and sample datasets for creating finetunes, with training instructions for user datasets.github.com · read 12 Oct 2026
- Deployment
- The repository documents local inference and one-click deployment through Baseten, which it calls its preferred inference partner.github.com · read 13 Oct 2026
- Emotion controls
- Speech characteristics can be guided with tags, including tags for laughter, sighs, coughing, and gasping.github.com · read 13 Oct 2026
- Export formats
- WAVgithub.com · read 20 Sep 2026
- Known limitations
- The repository checklist mentions an unresolved streaming issue that occasionally skips frames and a voice-cloning notebook implementation to fix.github.com · read 13 Oct 2026
- License
- The GitHub repository identifies its license as Apache-2.0.github.com · read 13 Oct 2026
- Limitations
- The README notes that the real-time streaming package may occasionally skip frames and lists fixing this as an open checklist item.github.com · read 12 Oct 2026
- Models
- The repository offers an English finetuned production model, a pretrained model trained on more than 100,000 hours of English speech, and a multilingual research release.github.com · read 13 Oct 2026
- Purpose
- Orpheus TTS is an open-source text-to-speech system built on a Llama 3B backbone.github.com · read 13 Oct 2026
- Speech capabilities
- The project describes natural intonation, emotion, and rhythm, plus voice cloning without prior fine-tuning.github.com · read 13 Oct 2026
- Speech controls
- Simple tags can guide speech and emotion characteristics, and the README lists tags such as <laugh>, <sigh>, and <gasp>.github.com · read 12 Oct 2026
- Speech quality
- The project describes its speech as having natural intonation, emotion, and rhythm.github.com · read 12 Oct 2026
