Format the script
Write lines with A>, B>, C> labels so each segment maps to a character.
ACTIVE · VERIFIED AGAINST THE PRODUCT
Text to Dialogue
Build multi-speaker audio from written dialogue. Assign a different voice to each speaker and control pauses between lines.
Verified operating specifications
Real inputs, limits and controls
- Speakers
- 2–26 speakers labeled A> through Z>
- Timing
- Per-speaker speed 0.5–1.5; segment delay 0–5 seconds
- Voice mix
- Different connected voice source for each character
- Extras
- Pronunciation dictionary, AI expression tags and optional transcript
Core capabilities
What this tool does
Multiple speakers
Voice per character
Pause controls
Unified voice library
Connected services
Related voice sources, services or models
ElevenLabsConnected service
MiniMaxVoice source
VbeeVoice source
Fish AudioVoice source
Microsoft Edge TTSConnected serviceProduct workflow
From input to finished output in three steps
Cast each speaker
Assign a voice and speed per character, then set the delay between segments.
Generate one conversation
Create the mixed dialogue and optionally export its timed transcript.
Use cases
Good fits
- Podcast conversations
- Training role-play
- Character scenes
- Multi-speaker localization
Developer API
Integrate this workflow
Generation tasks are asynchronous: receive a task_id, then poll or use a webhook.
POST/v3/text-to-speech/dialogueProduct-verified information
This page only describes capabilities visible in the current application with a corresponding processing path at the latest verification.