Built for voice agents that can't wait 600ms
Sign up freeSign in

Canopy Labs: Orpheus 3B

canopylabs/orpheus-3b
active tts 1 provider
Playground

Canopy Labs Orpheus 3B (0.1 finetuned) is an open (Apache-2.0) Llama-3.2-3B speech LLM for expressive, real-time text-to-speech with paralinguistic emotion tags, hosted on Together AI.

AuthorCanopy Labs
Languages1 languages
VoicesLoading...
Response formatsSynchronous: MP3 · WAV · PCM
Streaming: PCM
Statusactive

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer 1k charactersLatencyiFor TTS, latency is measured as time to first byte of audio. For STT, latency is measured as time to first token.ModesUptime
Together AI 7 params
together
$0.015
—
Synchronous · Streaming

Supported languages

1 languages
English en

Voices

Features

Text to speech

Generates spoken audio from text input.

text_to_speech
Streaming

Low-latency streaming TTS (~200ms).

streaming
Synchronous

Synthesizes speech from fully-submitted text in a single synchronous request.

synchronous
Paralinguistic emotion tags

Supports tags such as <laugh>, <chuckle>, <sigh>, <cough>, <yawn>, <gasp>.

emotion_tags

Code

Client
Mode
Language

ElevenLabs SDK streaming TTS

Routes the ElevenLabs SDK through allmodels and streams the audio response.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "canopylabs/orpheus-3b",
  outputFormat: "mp3_44100_128"
}, {
  queryParams: {
    provider: {
      "only": [
        "together"
      ]
    }
  }
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}