Audio Models

Here are all the audio models currently available in FLORA.

Speech & Voice

These models generate or transcribe speech.

Model	Est. time (s)	Description	Best for
ElevenLabs Multilingual v2	15	Natural text-to-speech with multilingual voice synthesis.	Voiceovers, narration, multilingual content, accessible media.
ElevenLabs Scribe v2	10	Transcribe speech to text.	Transcription, subtitles, meeting notes, content indexing.
Gemini 3.1 Flash TTS	10	Text to speech with prompted expressiveness.	Expressive voiceovers, character dialog, and stylized narration.

Sound Effects & Music

These models generate sound effects and music from text prompts.

Model	Est. time (s)	Description	Best for
Eleven v4	10	ElevenLabs' most expressive speech model, with audio tags for emotion, pacing and delivery across 90+ languages.	ElevenLabs' most expressive speech model, with audio tags for emotion, pacing and delivery across 90+ languages.
Eleven v4 Turbo	5	Low-latency Eleven v4 for fast, expressive speech with audio tags across 90+ languages.	Low-latency Eleven v4 for fast, expressive speech with audio tags across 90+ languages.
ElevenLabs Music v1	30	Generate music using a text prompt.	Background tracks, musical stings, and prompt-driven composition.
ElevenLabs Sound Effects	15	Generate sound effects and Foley from text descriptions.	Foley, ambient soundscapes, UI sounds, game audio.
ElevenLabs v3	15	Expressive multilingual text-to-speech. One voice holds its identity across languages.	Expressive multilingual text-to-speech. One voice holds its identity across languages.
Gemini 3 Flash	4	Google's fast and efficient text model.	Google's fast and efficient text model.
Lyria 3.5	40	Google DeepMind's music model. Full songs with vocals and lyrics from a text prompt. Set length, tempo, and structure in the prompt.	Google DeepMind's music model. Full songs with vocals and lyrics from a text prompt. Set length, tempo, and structure in the prompt.