Start creating

Canopy Labs

OrpheusAI text to speech

Open-weight speech with emotion tags such as <laugh> and <sigh>. On Leap, it sits beside 174 other models in one studio.

  • Text to speech

1 clip on Orpheus: $0.068. Your words wait while you sign in.

  • No subscription
  • Every top model, one account
  • Pay per run, priced before it starts

Listen / The fake plant, with a laugh and a sigh

0 / 9 s
Read the transcript

So I finally told him the plant was fake. <laugh> He'd been watering it for three years. <sigh> I just didn't have the heart to say it sooner.

AI text to speech

Orpheus at a glance

Orpheus is a text-to-speech model from Canopy Labs. It makes speech from your text.

Made by
Canopy Labs
Makes
Speech
Starts from
Your text
Voices
8 to choose from
Text
Up to 1,000 characters
Price per run
$0.068
Updated
October 3, 2026
  1. 01Write the words, pick a voice
  2. 02See the exact price, then press go
  3. 03Keep it in your library, or take it further

Start with an idea

Three ways to try Orpheus

Side by side

More voice and sound models on Leap

Why Leap

Why creators make it on Leap

  1. 01

    Every top model, side by side

    175 models from Black Forest Labs, Google, ByteDance, Kuaishou, Alibaba and more, side by side in one studio.

    See the models
  2. 02

    One click, or full control

    Character Studio, effects and recipes write the prompt for you. Or write your own for any model.

    See the tools
  3. 03

    Your work stays yours

    Everything you make stays in your library while your account is active, and you own what you make here.

    See what people make
  4. 04

    One balance for everything

    The studio, the API and your agents spend the same balance, and every run shows its price before it starts.

    How pricing works

Questions

Orpheus, answered

What is Orpheus?
Orpheus is a text-to-speech model from Canopy Labs. Open-weight speech with emotion tags such as <laugh> and <sigh>. On Leap it runs in one studio beside every other top model, with one account.
Which voices can I use?
8 voices, among them Tara, Leah, Jess, Leo and Dan. You can hear each one in the studio before you run it.
How much text can it read in one run?
Up to 1,000 characters. You pay for the characters you send, with the price shown before you press go.
How much does a run cost?
A run costs $0.068. You see the exact price before you press go, and a run that fails costs nothing.
Is Orpheus free to try?
No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.068 (a run), so $5 covers 73 of those. You pay per run, in dollars, with no subscription.
Can I use what I make commercially?
Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
Is there an API?
Yes. Leap's REST API runs it as canopy-labs/orpheus, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
Do I need a Canopy Labs account?
No. Leap sends your request to Canopy Labs' model and gives you what it makes. One Leap account runs Orpheus and every other model, in the studio, through the API and from your agents.

Your idea, Orpheus.

Every run shows its price before it starts, and one that fails costs nothing.

Make it with Orpheus

For developers

Run Orpheus from code

API docs
Model ID
canopy-labs/orpheus
Makes
Voice and sound
Pricing
Per run, quoted first: POST /v1/quotes

Inputs

What the model takes. Leave out anything with a default.

Texttext
Text, up to 1,000 characters, required
Voicevoice
Tara, Leah, Jess, Leo, Dan, Mia, Zac, Zoe. Default: Tara
Temperaturesettings.temperature
0 to 2. Default: 0.7Temperature for generation (higher = more creative).
Repetition Penaltysettings.repetition_penalty
1.1 to 2. Default: 1.2Repetition penalty (>= 1.1 required for stable generations).

The request

The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.

curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "canopy-labs/orpheus",    "input": {      "text": "So I finally told him the plant was fake. <laugh> He'\''d been watering it for three years. <sigh> I just didn'\''t have the heart to say it sooner."    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"