ByteDance
Seed Speech 2
ByteDance's speech model, in Chinese and English. On Leap, it sits beside 130 other models in one studio.
- Text to speech
- Start free, no card
- Every top model, one account
- Pay per run, priced before it starts
- 01Write the words, pick a voice
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Start with an idea
Three ways to try Seed Speech 2
Questions
Seed Speech 2 on Leap, answered.
- Is this the real Seed Speech 2?
- Yes. Leap sends your request to ByteDance's model through its provider and gives you back what it makes. Switch to any other model in the same studio when an idea needs it.
- What does it cost?
- In dollars, per run: the provider's list price plus 10%. You see the exact price before every run, a run that fails costs nothing, and there is no subscription. Every model's price is on the pricing page.
- Do I need a ByteDance account?
- No. One Leap account and one balance run Seed Speech 2 and every other model, in the studio, through the API and from your agents.
- What happens to what I make?
- It stays in your library while your account is active, ready to use anywhere.
Your idea, Seed Speech 2.
Start free, no card. Every run shows its price before it starts.
Make it with Seed Speech 2For developers
Run Seed Speech 2 from code
- Model ID
- bytedance/seed-speech-2
- 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 5,000 characters, required
Voicevoice
Stokie en, Vivi mixed en zh ja es id, Mindy en es id pt zh, Dacey en, Tim en, Kian en zh, Cedric en zh, Sophie en zh, Jean en zh, Magnus en zh, Mabel en zh, Nadia en zh, Opal en zh, Pearl en zh, Quentin en zh, Vienna mixed en zh, Alina mixed en zh, Corinne mixed en zh, Esther mixed en zh, Freya mixed en zh, Gigi mixed en zh, Holly mixed en zh, Lyla mixed en zh, Daisy mixed en zh, Tracy es zh, Jess ja es id pt en zh, Pinky es ko mixed en zh, Sweety ja es, Sandy es mixed en zh, Sven de, Minimi ja, Usseau fr, Felipe es, Han id, Martins pt, Enzo it, Shane ko, Bonnie zh, Felix zh, Celeste zh, Monkey king zh. Default: Stokie en
Sample Ratesettings.sample_rate
8000, 16000, 22050, 24000, 32000, 44100, 48000. Default: 24000Sample rate of the output audio in Hz.
Speedsettings.speed
0.5 to 2. Default: 1Speech speed.
Volumesettings.volume
0.5 to 2. Default: 1Volume.
Pitchsettings.pitch
-12 to 12. Default: 0Voice pitch shift in semitones.
Languagesettings.language
Zh, En, Ja, Es-mx, Id, Pt-br, Ko, It, De, FrForce the text to be read as a single language, disabling automatic language detection.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result. Agents can call it through the MCP server at mcp.tryleap.ai.
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": "bytedance/seed-speech-2", "input": { "text": "A paper boat drifting down a rainy street at dusk" } }'