All Voices Download (Basic+)
Basic Plan Audio Quality
High quality (44.1kHz)
Basic Plan Video Quality
Full HD (1080p)
Business Plan Voice Cloning Slots
2
Emotion Tags
normalslowcryingsleepysighchuckle
Free Tier Video Download Quality
HD (720p)
Guided Emotion and Intonation
HD Audio Downloads (Basic+)
44.1kHz
High Quality Speech Synthesis
Input Streaming for Lower Latency
Language Support (Flagship)
EnglishSpanishKoreanJapaneseChineseVietnamese
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Natural Variation in Speech
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Pro Plan Video Quality
Ultra HD (4K)
Pro Plan Voice Cloning Slots
1
Sample Finetuning Scripts
Sliding Window Detokenizer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Training Data Volume
100k+ hours of speech, billions of text tokens
Unlimited Voice Generation
Voice Customization Options
Voice Types
KidTikTokAudiobooksVoicemailsAnimeRapperNewsAnnouncerPodcastsAdsVideo gameCartoonNarration
Watermark-Free Downloads (Basic+)