TikTok comment voice note, 60 seconds: avatar script to mp3 for $11.05

A 60 second spoken reply for a comment costs $11.05 on Sume: a 60 second avatar job on the standard tier ($11.04) and an mp3 extraction with audio detach ($0.01). Metricool reports that TikTok comments now accept voice notes up to 60 seconds, so the audio fits the limit exactly.

This is an audio file you make yourself and add through the app. Sume does not post comments, and there is no documented way here to attach a file to a TikTok comment from the API.

The route

Generate the avatar talking video from a script, then detach the audio as mp3. The talking video is the expensive part because it renders a person; the audio is only the sound track from it.

• POST /v1/avatar-1.0/talking-video with a script and your avatar_handle, for 4 to 60 seconds.
• POST /v1/audio-detach with the resulting video URL and format mp3 (128 kbps). Default is wav.
• Download the file and upload it as a comment voice note in the app.

Cost by tier

The tier sets the per second rate. The detach is a flat $0.01, and the source video may be up to 1800 seconds.

Detach request

The source needs an audio track or the job fails with detach_source_has_no_audio. Avatar videos carry their voice.

curl -X POST https://api.sume.com/v1/audio-detach \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: voice-note-reply-12" \
  -d '{"video_url":"https://media.sume.com/artifacts/artf_demo/reply.mp4","format":"mp3"}'

Is it worth it

For a single reply, a plain recording is free. The route pays when you want a branded, repeatable voice across many replies, or an on-screen avatar and a voice note from one script. Keep the script near 150 words for 60 seconds, and test a shorter one first.