Knowledge base · audio
ElevenLabs
An audio studio: text-to-speech (TTS) in different languages with a choice of voice, music and sound effects, speech-to-text transcription, voice isolation and voice changing.
Open in studio →What it can do
- ✓Text-to-speech (TTS): natural speech in many languages, voice selection.
- ✓Music and sound effects from a text description.
- ✓Speech-to-text transcription: attach audio, get text.
- ✓Voice isolation (removing the background) and voice changing in a recording.
How to write a prompt
For speech: paste the text with punctuation (periods and commas set the pauses) and pick a voice. For music/SFX: describe the genre, mood, instruments and tempo. For transcription: attach an audio file (the cleaner the recording, the more accurate the text).
A prompt that works
Voiceover: "Welcome to Pixyn. Create images and videos in seconds.", calm, friendly voice
Avoid this
“make it nice”
Neither the text, nor the voice, nor the mood is set. Say what to voice or generate, with what voice or in what style.
Examples
Video voiceover
Voice the text with a calm female voice, warm intonation, moderate pace
Background music
Light background music for an intro: soft piano, warm ambient, no drums
Variants within the group
- Speech (TTS) / Music / Effects, Audio generation from text, pick the mode for the task.
- Transcription (STT) / Isolation / Voice change, Working with uploaded audio: text from speech, background cleanup, voice replacement.
Tips
- →Punctuation in the text controls pauses and intonation.
- →For long voiceovers, split the text into paragraphs.
FAQ
How much does a generation in ElevenLabs cost?
from 2 to 40 tokens per generation, depending on the chosen version and settings. Current plans and token packs are on the /en/pricing page.
Can the results of ElevenLabs be used commercially?
Yes, with an active Pixyn subscription. Note that some models have provider restrictions by industry, check the terms of the specific version.