- Support
- Integrations
- ElevenLabs
ElevenLabs
AI integration · 3 node(s).
00Overview
Every field below is exactly what you see in the Flomation editor. Fields marked ● live picker let you choose from a list pulled live from your account — no IDs to look up.
01Connecting ElevenLabs
Add your credentials as a Flomation environment secret, then pick them in each node. The connection fields are:
| Field | Type | Details | |
|---|---|---|---|
| ElevenLabs API Key | secret | Required | sk_... |
Pick an Environment on your flow (Flow Settings → Environment) so the secret resolves. Secret fields never show the value — they reference ${secrets.your_secret}.
02List
List Voices
elevenlabs/list_voices · Action
List all available ElevenLabs voices with their IDs, names, and characteristics
Returns: tool_result, voices, count, success, error
03Speech
Speech to Text
elevenlabs/speech_to_text · Action
Transcribe audio to text using ElevenLabs speech recognition
| Field | Type | Details | |
|---|---|---|---|
| Audio data (base64-encoded). Provide this OR audio_url. | string | ${voice_audio_base64} | |
| URL to audio file. Provide this OR audio_base64. | string | https://example.com/audio.mp3 | |
| Language code (ISO 639-1, e.g. 'en', 'fr', 'de'). Leave empty for auto-detect. | string | en | |
| Model | string | choices: Scribe v1 (default) |
Returns: tool_result, text, language_code, words, success, error
04Text
Text to Speech
elevenlabs/text_to_speech · Action
Convert text to spoken audio using ElevenLabs AI voices
| Field | Type | Details | |
|---|---|---|---|
| Text to convert to speech | text | Required | Hello, welcome to Flomation! |
| Voice ID (from list_voices, or use a name like 'Rachel', 'Adam') | string | Required | 21m00Tcm4TlvDq8ikWAM |
| Model | string | choices: Multilingual v2 (best quality), Turbo v2.5 (low latency), Turbo v2 (low latency), English v1 | |
| Stability (0.0-1.0, higher = more consistent, lower = more expressive) | string | 0.5 | |
| Similarity Boost (0.0-1.0, higher = closer to original voice) | string | 0.75 | |
| Style exaggeration (0.0-1.0, v2 models only) | string | 0.0 | |
| Use Speaker Boost (enhances voice clarity and presence) | boolean | ||
| Output Format | string | choices: MP3 (44.1kHz, 128kbps), MP3 (44.1kHz, 64kbps), MP3 (22.05kHz, 32kbps), PCM (16kHz), PCM (22.05kHz), PCM (24kHz), PCM (44.1kHz), u-law (8kHz, telephony) |
Returns: tool_result, audio_base64, audio_format, audio_size_bytes, character_count, success, error
05Notes & Limitations
Behaviours and constraints worth knowing before you build with these nodes.
- Text to Speech is billed against your ElevenLabs character allowance by the length of the input text, not by the duration of the audio produced, so long passages consume quota quickly regardless of how the speech sounds.
- Text to Speech returns the audio as base64-encoded data rather than a ready-made file, so pair it with a downstream node that accepts base64 audio to save, send, or play the result.
- Text to Speech and Speech to Text requests are cut off after 120 seconds, so very long text or large source audio can time out before the node finishes.
- Generated and transcribed audio is capped at 50 MB, and anything beyond that limit is silently truncated rather than raising an error, so keep individual clips well under that size.
- List Voices returns only the voices your API key's account can reach, so cloned or professional voices appear here only after they have been created in your ElevenLabs workspace.