Audio models

AI models for speech recognition, synthesis, and audio processing with verifiable specifications and sources.

Gemini Omni Audio

Google

Gemini Omni Audio is part of Google's Gemini Omni family. This card is for an audio workflow. It can create or transform audio material. Consider it when the desired result is sound, speech, or music. Input: Audio, Images; output: Audio.

Audio modelsExternal model, reference pageGemini Omni Audio: For audio workflows, it can create or transform audio material.Input: Audio, Images; output: Audio.

ElevenLabs Audio Isolation

ElevenLabs

ElevenLabs Audio Isolation is part of ElevenLabs's ElevenLabs family. This card is for an audio workflow. It can isolate useful voice or sound from a noisy recording. Consider it when the recording needs cleanup before editing, transcription, or publishing. Input: Audio; output: Audio.

Audio modelsExternal model, reference pageElevenLabs Audio Isolation: For audio workflows, it can isolate useful voice or sound from a noisy recording.Input: Audio; output: Audio.

ElevenLabs Text to Dialogue v3

ElevenLabs

ElevenLabs Text to Dialogue v3 is part of ElevenLabs's ElevenLabs family. This card is for an audio workflow. It can voice a dialogue with multiple speakers. Consider it when text needs to become a conversation, scene, or podcast segment. Input: Text; output: Audio.

Audio modelsExternal model, reference pageElevenLabs Text to Dialogue v3: For audio workflows, it can voice a dialogue with multiple speakers.Input: Text; output: Audio.

ElevenLabs Text to Speech Multilingual v2

ElevenLabs

ElevenLabs Text to Speech Multilingual v2 is part of ElevenLabs's ElevenLabs family. This card is for an audio workflow. It can turn text into natural-sounding speech. Consider it when you need narration, a voice-over, or a spoken interface. Input: Text; output: Audio.

Audio modelsExternal model, reference pageElevenLabs Text to Speech Multilingual v2: For audio workflows, it can turn text into natural-sounding speech.Input: Text; output: Audio.

ElevenLabs Text to Speech Turbo 2.5

ElevenLabs

ElevenLabs Text to Speech Turbo 2.5 is part of ElevenLabs's ElevenLabs family. This card is for an audio workflow. It can turn text into natural-sounding speech. Consider it when you need narration, a voice-over, or a spoken interface. Input: Text; output: Audio.

Audio modelsExternal model, reference pageElevenLabs Text to Speech Turbo 2.5: For audio workflows, it can turn text into natural-sounding speech.Input: Text; output: Audio.

Gemini 3.1 Flash Text to Speech

Google

Gemini 3.1 Flash Text to Speech is part of Google's Gemini TTS family. This card is for an audio workflow. It can turn text into natural-sounding speech. Consider it when you need narration, a voice-over, or a spoken interface. Input: Text; output: Audio.

Audio modelsExternal model, reference pageGemini 3.1 Flash Text to Speech: For audio workflows, it can turn text into natural-sounding speech.Input: Text; output: Audio.

Gemini 2.5 Pro Text to Speech

Google

Gemini 2.5 Pro Text to Speech is part of Google's Gemini TTS family. This card is for an audio workflow. It can turn text into natural-sounding speech. Consider it when you need narration, a voice-over, or a spoken interface. Input: Text; output: Audio.

Audio modelsExternal model, reference pageGemini 2.5 Pro Text to Speech: For audio workflows, it can turn text into natural-sounding speech.Input: Text; output: Audio.

Suno Music Generation

Suno

Suno Music Generation is part of Suno's Suno family. This card is for an audio workflow. It can create, transform, or continue musical material. Consider it when the task involves composition, vocals, arrangement, or sound design. Input: Text; output: Audio.

Audio modelsExternal model, reference pageSuno Music Generation: For audio workflows, it can create, transform, or continue musical material.Input: Text; output: Audio.

Suno Music Extension

Suno

Suno Music Extension is part of Suno's Suno family. This card is for an audio workflow. It can extend an existing video or music segment. Consider it when a successful source needs a coherent continuation. Input: Text, Audio; output: Audio.

Audio modelsExternal model, reference pageSuno Music Extension: For audio workflows, it can extend an existing video or music segment.Input: Text, Audio; output: Audio.

Suno Upload and Cover Audio

Suno

Suno Upload and Cover Audio is part of Suno's Suno family. This card is for an audio workflow. It can create, transform, or continue musical material. Consider it when the task involves composition, vocals, arrangement, or sound design. Input: Text, Audio; output: Audio.

Audio modelsExternal model, reference pageSuno Upload and Cover Audio: For audio workflows, it can create, transform, or continue musical material.Input: Text, Audio; output: Audio.

Suno Upload and Extend Audio

Suno

Suno Upload and Extend Audio is part of Suno's Suno family. This card is for an audio workflow. It can extend an existing video or music segment. Consider it when a successful source needs a coherent continuation. Input: Text, Audio; output: Audio.

Audio modelsExternal model, reference pageSuno Upload and Extend Audio: For audio workflows, it can extend an existing video or music segment.Input: Text, Audio; output: Audio.

Suno Add Instrumental

Suno

Suno Add Instrumental is part of Suno's Suno family. This card is for an audio workflow. It can create, transform, or continue musical material. Consider it when the task involves composition, vocals, arrangement, or sound design. Input: Audio; output: Audio.

Audio modelsExternal model, reference pageSuno Add Instrumental: For audio workflows, it can create, transform, or continue musical material.Input: Audio; output: Audio.

Suno Add Vocals

Suno

Suno Add Vocals is part of Suno's Suno family. This card is for an audio workflow. It can separate a music recording into vocal and instrumental components. Consider it when separate tracks are needed for remixing, analysis, or a new mix. Input: Audio, Text; output: Audio.

Audio modelsExternal model, reference pageSuno Add Vocals: For audio workflows, it can separate a music recording into vocal and instrumental components.Input: Audio, Text; output: Audio.

Suno Replace Music Section

Suno

Suno Replace Music Section is part of Suno's Suno family. This card is for an audio workflow. It can transform an existing video without reshooting the source scene. Consider it when you need to change the style, subject, character, or part of a clip. Input: Audio, Text; output: Audio.

Audio modelsExternal model, reference pageSuno Replace Music Section: For audio workflows, it can transform an existing video without reshooting the source scene.Input: Audio, Text; output: Audio.

Suno Persona

Suno

Suno Persona is part of Suno's Suno family. This card is for an audio workflow. It can create, transform, or continue musical material. Consider it when the task involves composition, vocals, arrangement, or sound design. Input: Audio, Text; output: Audio.

Audio modelsExternal model, reference pageSuno Persona: For audio workflows, it can create, transform, or continue musical material.Input: Audio, Text; output: Audio.

Suno Mashup

Suno

Suno Mashup is part of Suno's Suno family. This card is for an audio workflow. It can create, transform, or continue musical material. Consider it when the task involves composition, vocals, arrangement, or sound design. Input: Audio, Text; output: Audio.

Audio modelsExternal model, reference pageSuno Mashup: For audio workflows, it can create, transform, or continue musical material.Input: Audio, Text; output: Audio.

Suno WAV Conversion

Suno

Suno WAV Conversion is part of Suno's Suno family. This card is for an audio workflow. It can create or transform audio material. Consider it when the desired result is sound, speech, or music. Input: Audio; output: Audio.

Audio modelsExternal model, reference pageSuno WAV Conversion: For audio workflows, it can create or transform audio material.Input: Audio; output: Audio.

Suno Stem Separation

Suno

Suno Stem Separation is part of Suno's Suno family. This card is for an audio workflow. It can separate a music recording into vocal and instrumental components. Consider it when separate tracks are needed for remixing, analysis, or a new mix. Input: Audio; output: Audio.

Audio modelsExternal model, reference pageSuno Stem Separation: For audio workflows, it can separate a music recording into vocal and instrumental components.Input: Audio; output: Audio.

Suno MIDI Generation

Suno

Suno MIDI Generation is part of Suno's Suno family. This card is for an audio workflow. It can turn a musical idea into an editable MIDI representation. Consider it when the material needs further work in a sequencer or arrangement. Input: Audio; output: Audio.

Audio modelsExternal model, reference pageSuno MIDI Generation: For audio workflows, it can turn a musical idea into an editable MIDI representation.Input: Audio; output: Audio.

Suno Sounds

Suno

Suno Sounds is part of Suno's Suno family. This card is for an audio workflow. It can create, transform, or continue musical material. Consider it when the task involves composition, vocals, arrangement, or sound design. Input: Text; output: Audio.

Audio modelsExternal model, reference pageSuno Sounds: For audio workflows, it can create, transform, or continue musical material.Input: Text; output: Audio.

Suno Custom Voice

Suno

Suno Custom Voice is part of Suno's Suno family. This card is for an audio workflow. It can create or transform audio material. Consider it when the desired result is sound, speech, or music. Input: Audio, Text; output: Audio.

Audio modelsExternal model, reference pageSuno Custom Voice: For audio workflows, it can create or transform audio material.Input: Audio, Text; output: Audio.

How to read this category

This page groups models of one type, but they solve different jobs. Start from the use case, not the model name: it is the shortest path to a usable result without unnecessary reruns.

check purpose, modalities, and developer against reviewed sources
separate models available in Neiron from market information pages

Practical choice

Availability in Neiron is confirmed only by the internal product catalog.
Unverified benchmarks and specifications are not published.

Back to catalog