Turn a script into spoken audio with the currently available provider/model controls, including Azure MAI Voice and ElevenLabs routes where offered. Pricing is operation- and text-length-based, so check the live quote after choosing a voice and entering the final script.
Where: canvas → left rail → Add → Audio → Gen Voice — Add an AI Voice node and connect or type a script
Key ideas
- Voice + model: Choose from the models currently exposed by this node, including Azure MAI Voice 2.1/Flash and ElevenLabs routes where available. Voice IDs belong to their provider namespace; switching providers does not make a saved voice ID portable.
- Provider-specific voice controls: Controls depend on the selected route. Azure MAI Voice exposes managed voices, supported speaking styles, and MP3/WAV output; do not assume a language, emotion, or style control applies to every provider.
- Text limits and quote units: Azure MAI Voice is quoted per started 250 text characters, up to 5,000 characters. ElevenLabs v4/Turbo are also quoted per started 250-character block, with audio tags counted and a 5,000-character Turbo limit. The node’s refreshed quote is authoritative.
- Audio output: The node outputs audio (audio_out) you can wire into an Avatar or a Video composition; results are versioned and persisted.
- Gen Voice card: VoiceGenerationNode uses the generic shared-card path. Generate speech from text with a selected model, voice, language, emotion/delivery, and speed.
- Properties sidebar: renderAudioNodes.tsx
- Opened surfaces: Audio preview
Steps
- Add a Voice Generator node and type your script (or connect a Text node to its prompt).
- Choose a currently offered model and select a voice from that provider’s catalog.
- Set only the language, style, or output-format controls shown for the selected model.
- Enter the final script, including any supported audio tags, then review the updated quote; character-block pricing can increase as text grows.
- Click Generate; preview the audio, then download or wire audio_out downstream.
Card and inspector fields
- Model and voice.
- Language and system prompt.
- Emotion/delivery controls.
- Speed from 0.5× to 2× in the shared UI; provider routes may clamp or convert it to a delivery instruction.
Opened surface
Audition every version in the audio preview before using it in Lip Sync, Digital Twin, Audio Render, or Video Composition.
Gen Voice controls and presets
- Add path: Flowgen → Add → Sound → Gen Voice.
- Card: VoiceGenerationNode.
- Properties: renderAudioNodes.tsx.
- Controls: Model; voice; language; system prompt; emotion; speed; versions.
- Opened surfaces: Audio preview.
FAQ
Why did my quote change after editing the script?
Several current routes bill by started text blocks. Azure MAI Voice and ElevenLabs v4/Turbo use 250-character units; audio tags count on the ElevenLabs route. Re-read the live quote after the final text and voice are set.