Getting started
Open @AuxioBot, send a voice message, a file or a link to get the text, or open the mini app to make a song, music, a sound effect or a voice-over.
Open a chat with @AuxioBot and press Start. The main screen shows your free allowance and lists what the bot does.
The first line of the header counts the free transcription minutes, the second the free generations. When the first 3 generations are used, it shows the free credits of the week instead, and your purchased balance once you have one.
Transcribe a recording
There is nothing to choose first. Do one of these:
- Record or forward a voice message or a round video note to the bot.
- Send an audio or video file, as audio, as video or as a document.
- Paste a link to a video. The bot opens it, checks the length and starts working.
A short voice message comes back as a plain text message. A long recording or a link comes back as one message with a collapsible text, a file, a summary and a block with timecodes.
The "Transcribe a file" button
Transcribe a file opens a short animated how-to and reminds you what it costs: the first 30 minutes or 5 recordings are free, then 1 credit per minute. Under it are the transcription buttons:
- Settings: the file format (TXT, Markdown, Word or PDF) and the language hint. See formats and summary.
- Transcript history: your last 10 transcripts, to keep asking about one. See questions about a transcript.
- Transcription in groups: add the bot to a group chat. See transcription in groups.
The same screens open with the /settings and /history commands.
Make a track
Press Music & Sound Creation or Text to Speech. The bot shows a short demo and the buttons Open in Telegram and Open in browser; both open the mini app on the right form:
- Music & Sound Creation: a song, instrumental music or a sound effect. See songs, music and sound effects.
- Text to Speech: a voice-over of your text. See text to speech.
Describe what you want, pick the length or the voice and press Start Generation. The track arrives in your chat with the bot as an audio message. All your tracks are kept under My audio, see My audio.
One task at a time
The bot transcribes one recording per user at a time: if you send a second one while the first is still being processed, it asks you to wait for the result. The same goes for generation: wait for the previous track before you start the next.
If the recording has no speech, or the file is not audio or video, the bot says so and does not charge anything. If a generation fails, its credits are returned.