Skip to main content
ElevenLabs logo

ElevenLabs

The full ElevenLabs audio suite, built in on your FlyMyAI account: speech synthesis and transcription plus voice isolation, sound effects, voice changing, voice design, and dubbing. This is the preferred audio stack for agents.

What it can do

MethodWhat it does
text_to_speechText to speech → audio agent_file (use result.agent_file.public_url, e.g. send_voice).
speech_to_textScribe transcription - exactly one of audio_base64 / cloud_storage_url / source_url.
audio_isolationRemove background noise/music from a voice recording → cleaned audio.
generate_sound_effectText description → a sound effect.
speech_to_speechVoice changer - convert source audio into a target voice.
design_voice + create_voice_from_previewVoice Design: describe a voice, preview options, then save one.
dubbing_createdubbing_statusdubbing_audioTranslate / dub audio or video into another language.
get_voices / get_voice / list_modelsDiscover available voices and models.
list_history / get_user_subscriptionRecent generations; credit balance and limits.

Audio inputs accept audio_base64 or audio_url (a public HTTPS URL such as a prior agent_file.public_url).

How to get credentials

  1. Sign in at elevenlabs.io.
  2. Open Profile + API key (top right) or go to elevenlabs.io/app/settings/api-keys.
  3. Copy the API key and paste it in FlyMyAI.

Fields to fill in FlyMyAI

FlyMyAI fieldWhere it comes from
ELEVENLABS_API_KEYelevenlabs.io → Settings → API keys

Troubleshooting

  • quota_exceeded - character quota on your plan is used up. Wait for reset or upgrade.
  • Voice not found - call get_voices to list IDs available to your account; voices shared by other users may not be copied to yours.
We love our partners - FlyMy.AI builds with the best. Thanks, ElevenLabs!