Ready-to-use Agent

Turn text into MP3 voiceovers and subtitles

Generate downloadable MP3 speech and SRT subtitles from English, Chinese, and other supported languages. Useful for short videos, tutorials, and multilingual content.

AvailableMedia Audiomedia-audio
Give it a task nowDescribe what you need first. After sign-in and Agent setup, this exact request will be sent to chat.
Edit freely before submitting. Nothing runs until you continue.
Watch the Agent demo36.501s

A Chinese-language walkthrough showing how the Agent turns multilingual text into MP3 voiceovers and SRT subtitles, with voice, speed, pitch, and volume controls.

Watch on the dedicated demo page →
01

What it can deliver

This Agent uses rany2's open-source edge-tts project for online speech generation and verifies the resulting audio and subtitle artifacts. It requires network access; upstream availability is not an official SLA or a guarantee of unlimited free usage.

02

Good fits for this Agent

✓

Create MP3 voiceovers for short videos and social content

✓

Generate narration audio and SRT subtitles together

✓

Add voiceovers to tutorials, product demos, and lessons

✓

Choose an online voice and adjust speed, pitch, and volume

03

Start in three steps

Create the Agent, connect your supported Owner control channel and the business context it needs, then assign work, approve sensitive actions, and review the result in chat.

1Create the Agent

No infrastructure or runtime selection required.

2Connect work context

Provide the required material and a supported Owner control channel.

3Assign and review

Give it work, approve sensitive actions, and review delivery.

04

Open-source capability credits

ClawMama integrates, validates, and packages upstream open-source capabilities. This does not imply endorsement by upstream maintainers.

edge-ttsrany2/edge-tts
Online multilingual text-to-speech CLI and subtitle generationLGPL-3.0 (srt_composer.py: MIT)↗
FAQ

FAQ

Can it generate voice and subtitles together?

Yes. The Agent can produce an MP3 audio file and, when requested, a matching SRT subtitle file.

Which languages and voices are supported?

It can query the currently available online voices and generate speech using the languages and voices exposed by edge-tts at that time. The list can change with the upstream service.

Do I need a separate API key?

The current workflow does not require a separate speech-service API key, but it does require network access and does not guarantee long-term upstream availability or unlimited free usage.