Official BytePlus partnerBuilt on BytePlus, ByteDance's official AI platform
Guide · Audio
Two-speaker AI dialogue: step by step
Make a two-voice dialogue in Text to Speech: cast Speaker A and B, write up to 12 turns of 600 characters, generate and play it in order. With pricing and tips.
- Two speakers
- Up to 12 turns
- 600 characters per turn
Short answer
In Text to Speech, switch to "Two speakers", pick a voice for Speaker A and one for Speaker B, write up to 12 turns of up to 600 characters, generate, and "Play all" plays it in order. Each turn is billed as its own clip at 1 credit per 1,000 characters.
Updated:
Step by step
- 1
Switch to Two speakers
Open Text to Speech and choose the "Two speakers" mode.
- 2
Cast Speaker A and Speaker B
Pick two of 45 voices in 14 languages, or your own cloned voice under "My Voices". Two contrasting voices are easier to tell apart.
- 3
Write the turns
Add up to 12 turns of up to 600 characters and set who speaks each one.
- 4
Generate
Each turn is generated in its speaker's voice, one after the other.
- 5
Listen and download
"Play all" plays the dialogue in order. Every line has its own player and download, ready for your editor.
Example dialogue
One turn per line; A and B take turns.
A
Welcome back. Today we're talking about making a video in one afternoon.
B
And the short answer is: start with the script, not the camera.
A
Fair. So how long should that script be?
B
For a short, about twenty-five words is plenty.
How to write a good dialogue
Natural dialogue is written for the ear.
- Short turns: one or two sentences per line.
- Let the characters use each other's names now and then.
- Add short reactions ("Fair.", "Really?") for rhythm.
- For long episodes, write in segments and join them in an editor.
Alternative: a described scene in Audio Generation
If you would rather describe the scene than script it turn by turn, Audio Generation can voice two characters from one prompt with "Speaker A:" and "Speaker B:" lines. Its voices come from the prompt and can change between runs; Text to Speech keeps the same two voices every time.
What it costs
Each turn is billed as its own clip at 1 credit per 1,000 characters, with a minimum of 1 credit per turn. A full dialogue of 12 turns at 600 characters costs 12 credits.
Frequently asked questions
Can there be more than two voices?
Not in one dialogue: there is Speaker A and Speaker B. For more characters, generate several dialogues and join them in an editor.
Can the speakers use different languages?
Yes. Each speaker can use any voice, so A can speak English and B Spanish.
Does it download as one file?
Each line downloads separately. "Play all" plays them in order in the studio, and an editor joins them into one file.
Try it in the studio
New accounts get 75 starter credits for images and video. Free accounts can make video on Seedance 2 Fast and Seedance 2.0 Mini at 480p, queued and rate limited. A plan adds every video model, 720p and above, and no queue. The cost is shown before every generation.