Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free trial
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • LLM cost calculator
  • Token counter
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Benchmarks
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
Help Center
🔈

Listening to replies

Found this helpful? Share it:

Every reply can be read out loud, so you can listen instead of reading: catch up while you do something else, or hear how a draft sounds 🔊

Play a reply out loud

Hover over any assistant reply and click the speaker button. idapt reads the reply sentence by sentence in your current voice. Click the button again (it becomes a stop button while playing) to stop.

The speaker even shows while a reply is still streaming in, so you can start listening right away and it keeps reading as the rest arrives.

Play a whole run

A single answer can span several messages while the assistant works. Use the run-level play control to hear the whole thing read in order. Once it is playing, every message in the queue shows a stop button, and clicking any of them stops the whole run.

Pick the voice and model

Choose the voice, model, and speed in Settings → Voice Mode. These are the same settings voice mode uses, so what you hear on playback matches what you hear in a spoken conversation. See Talking to idapt with your voice. Change the voice and the next playback regenerates in the new one.

Replays are free

The first time a reply is spoken it is generated and billed like any audio. After that it is cached, so replaying the same reply, or hearing a spoken answer again, costs nothing.

Playback is not tied to a plan. It is metered per use like other audio, and cached replays are free.

Want to turn your own text into a saved audio file instead? See Audio generation.

Related articles

🎙️

Talking to idapt with your voice

Dictate a message, hold a full spoken conversation, and hear any reply read back to you.

🔊

Audio generation

Turn text into natural-sounding speech, with a voice and model you choose.

Up next

Subagent conversations

Let agents delegate parts of a complex request to worker conversations.

Was this helpful?