Skip to content
SPECIFICTION
Get listed

Orpheus TTS

github.com

APISelf-hosted
Visit github.com
Spec score 7.4 #171 of 223 in Text-to-Speech Software

Spec sheet

Purpose
Orpheus TTS is an open-source text-to-speech system built on a Llama 3B backbone.Read 13 Oct 2026 · github.com
Platforms
api,self_hostedRead 20 Sep 2026 · github.com
Deployment
The repository documents local inference and one-click deployment through Baseten, which it calls its preferred inference partner.Read 13 Oct 2026 · github.com
License
The GitHub repository identifies its license as Apache-2.0.Read 13 Oct 2026 · github.com
Headquarters
San Francisco, California, United StatesRead 28 Sep 2026 · github.com
API access
YesRead 20 Sep 2026 · github.com
Baseten deployment
The Baseten model page lists text input, audio output, Apache 2.0 licensing, and H100 MIG 40GB hardware.Read 12 Oct 2026 · baseten.co
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.Read 12 Oct 2026 · baseten.co
Commercial use
YesRead 20 Sep 2026 · github.com
Company focus
Canopy Labs describes itself as building realtime interactive models for avatars.Read 13 Oct 2026 · canopylabs.ai
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.Read 13 Oct 2026 · orpheus.canopylabs.ai
Customization
The README provides data-processing scripts and sample datasets for creating finetunes, with training instructions for user datasets.Read 12 Oct 2026 · github.com
Emotion controls
Speech characteristics can be guided with tags, including tags for laughter, sighs, coughing, and gasping.Read 13 Oct 2026 · github.com
Export formats
WAVRead 20 Sep 2026 · github.com
Known limitations
The repository checklist mentions an unresolved streaming issue that occasionally skips frames and a voice-cloning notebook implementation to fix.Read 13 Oct 2026 · github.com
Limitations
The README notes that the real-time streaming package may occasionally skip frames and lists fixing this as an open checklist item.Read 12 Oct 2026 · github.com
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.Read 13 Oct 2026 · github.com
Speech capabilities
The project describes natural intonation, emotion, and rhythm, plus voice cloning without prior fine-tuning.Read 13 Oct 2026 · github.com
Speech controls
Simple tags can guide speech and emotion characteristics, and the README lists tags such as <laugh>, <sigh>, and <gasp>.Read 12 Oct 2026 · github.com
Speech quality
The project describes its speech as having natural intonation, emotion, and rhythm.Read 12 Oct 2026 · github.com
Streaming
The repository reports about 200 ms streaming latency, reducible to about 100 ms with input streaming.Read 13 Oct 2026 · github.com
Training
The repository provides data processing scripts and sample datasets for fine-tuning, and describes fine-tuning on text and speech.Read 13 Oct 2026 · github.com
Voice cloning
The project lists zero-shot voice cloning without prior fine-tuning as an ability.Read 12 Oct 2026 · github.com
Watermarking
The repository points to an implementation for watermarking generated audio with Silent Cipher.Read 13 Oct 2026 · github.com

Where Specifiction places it

Alternatives to Orpheus TTSAll alternatives →