⚡️ FlashAttention-4: up to 1.3× faster than cuDNN on NVIDIA Blackwell →

Introducing Together AI's new look →

🔎 ATLAS: runtime-learning accelerators delivering up to 4x faster LLM inference →

⚡ Together GPU Clusters: self-service NVIDIA GPUs, now generally available →

📦 Batch Inference API: Process billions of tokens at 50% lower cost for most models →

🪛 Fine-Tuning Platform Upgrades: Larger Models, Longer Contexts →

Models / Canopy Labs
Audio

Orpheus TTS

Human-level speech generation with natural emotion and intonation

Try Now
read docs

About model

Orpheus TTS is a breakthrough speech-LLM family built on Llama-3B that achieves human-level speech generation with natural emotion and intonation. Trained on 100k+ hours of English speech data, Orpheus demonstrates that open-source TTS can finally compete with—and surpass—closed-source models in real-world quality.

  • API usage

    • cURL
    • Python
    • Typescript

    Endpoint:

    canopylabs/orpheus-3b-0.1-ft

    curl --location 'https://api.together.ai/v1/audio/generations' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer $TOGETHER_API_KEY' \
  --output speech.mp3 \
  --data '{
    "input": "Today is a wonderful day to build something people love!",
    "voice": "helpful woman",
    "response_format": "mp3",
    "sample_rate": 44100,
    "stream": false,
    "model": "canopylabs/orpheus-3b-0.1-ft"
  }'

    from together import Together

client = Together()

speech_file_path = "speech.mp3"

response = client.audio.speech.create(
  model="canopylabs/orpheus-3b-0.1-ft",
  input="Today is a wonderful day to build something people love!",
  voice="helpful woman",
)
    
response.stream_to_file(speech_file_path)


    import Together from 'together-ai';

const together = new Together();

async function generateAudio() {
   const res = await together.audio.create({
    input: 'Today is a wonderful day to build something people love!',
    voice: 'helpful woman',
    response_format: 'mp3',
    sample_rate: 44100,
    stream: false,
    model: 'canopylabs/orpheus-3b-0.1-ft',
  });

  if (res.body) {
    console.log(res.body);
    const nodeStream = Readable.from(res.body as ReadableStream);
    const fileStream = createWriteStream('./speech.mp3');

    nodeStream.pipe(fileStream);
  }
}

generateAudio();

  • Model card

    Architecture Overview:
    • Llama-3B backbone architecture adapted for speech-LLM applications
    • Trained on 100k+ hours of English speech data and billions of text tokens
    • SNAC audio tokenizer with 7 tokens per frame decoded as flattened sequence
    • CNN-based detokenizer with sliding window modification for streaming without popping

    Training Methodology:
    • Pretrained on massive scale speech and text data to maintain language understanding
    • Text token training boosts TTS performance while preserving semantic reasoning ability
    • Trained exclusively on permissive/non-copyrighted audio data
    • Fine-tuned models available for production use with 8 distinct voices (tara, leah, jess, leo, dan, mia, zac, zoe)
    • Supports custom fine-tuning with as few as 50 examples per speaker

    Performance Characteristics:
    • Handles disfluencies naturally without artifacts
    • Streaming inference faster than real-time playback on A100 40GB for 3B parameter model
    • vLLM implementation enables efficient GPU utilization

  • Applications & use cases

    Conversational AI & Virtual Assistants:
    • Low-latency streaming enables natural conversational experiences
    • Emotional intelligence and empathy expression for human-like interactions
    • Multiple voice options for personalized assistant experiences
    • Handles natural disfluencies and conversational patterns

    Content Creation & Media:
    • Audiobook narration with natural emotion and intonation
    • Podcast generation with multiple speaker voices
    • Video voiceovers with guided emotion control
    • Character voices for gaming and animation

    Enterprise & Production Applications:
    • Contact center automation with empathetic customer service voices
    • E-learning and training content with engaging narration
    • Accessibility applications for text-to-speech needs
    • Real-time translation and dubbing services

    Creative Applications:
    • Guided emotion and intonation for dramatic readings
    • Role-playing and character voice generation
    • Music and audio production with vocal synthesis
    • Interactive storytelling with dynamic voice expressions

    ‍

Related models
new
Audio
MiniMax Speech 2.6 Turbo
  • Deployment
    Dedicated Inference
No items found.
Audio
new
Audio
Arcana V3
  • Deployment
    Dedicated Inference
No items found.
Audio
New
Audio
Cartesia Sonic-3
  • Input/1M
    $65.00
  • Context
    Unlimited
No items found.
Audio
Model specifications
Model data
  • Model provider
    Canopy Labs
  • Type
    Audio
  • Main use cases
    Small & Fast
    Text-to-Speech
  • Deployment
    Serverless
  • Endpoint
    canopylabs/orpheus-3b-0.1-ft
  • Parameters
    3B
  • Price

    $0.27 / 1M characters

  • Price

    $0.85 / 1M characters

  • Input modalities
    Text
  • Output modalities
    Audio
  • Released
    March 16, 2025
  • Last updated
    November 2, 2025
  • External link
    Provider docs
  • Category
    Audio
Run in Playground
Quickstart docs
Deploy model