Audio Translator

Translate recordings by voice

Pick a podcast clip, a voice-over, a lesson or an interview from your MegaScenes library and choose the language: Spanish, French, German, Japanese and more. You get the recording back in that language, spoken in the same voices.

MCP connector

Server URL: https://audio-translator.megascenes.com/api/chatgpt/audio-translator/mcp
Login: OAuth
Protocol: MCP 2025-11-25
Instructions: Translates a recording in the person's library into another language, keeping the speakers' voices: gives the asset_id and length of their recordings. Only their own recordings or ones whose speakers agreed, never a famous person's voice: decline those. The price follows the length of the recording, by started minute: give it with (pass video_seconds, the recording's length), call only when asked (without input_asset_ids if they have no recording yet: the result says how to add one), then every 30 seconds until it is done; it takes a few minutes. Costs are in credits. Failed runs are refunded automatically. The model list and credit costs work signed out; creating needs the person's MegaScenes account. Not for sexual, nude or other adult content, or for the voice of anyone but the person themselves or speakers who agreed to it, nor of famous people: decline those requests without calling the tools. When a result says the account lacks credits, say so; credits are managed in the person's account outside ChatGPT.

Tools

Reads data5

Changes data1

Skills

None in the store listings or on the server

MCP connector

Server URL

https://audio-translator.megascenes.com/api/chatgpt/audio-translator/mcp

OAuth

Protocol

MCP 2025-11-25

Instructions

Translates a recording in the person's library into another language, keeping the speakers' voices: gives the asset_id and length of their recordings. Only their own recordings or ones whose speakers agreed, never a famous person's voice: decline those. The price follows the length of the recording, by started minute: give it with (pass video_seconds, the recording's length), call only when asked (without input_asset_ids if they have no recording yet: the result says how to add one), then every 30 seconds until it is done; it takes a few minutes. Costs are in credits. Failed runs are refunded automatically. The model list and credit costs work signed out; creating needs the person's MegaScenes account. Not for sexual, nude or other adult content, or for the voice of anyone but the person themselves or speakers who agreed to it, nor of famous people: decline those requests without calling the tools. When a result says the account lacks credits, say so; credits are managed in the person's account outside ChatGPT.