AI Audio Generator
Generate, remix, and extend music; create speech and sound effects from text; or generate audio that matches a video. All exposed through the same MuApi JSON API with the standard submit-and-poll flow.
- →Music: Suno create / remix / extend
- →Sound effects & ambience: MMAudio text-to-audio, MMAudio video-to-audio
- →Pair with lipsync for end-to-end dubbed video pipelines
Quick Start
Every model in this category uses the same submit-then-poll API. Replace suno-create-music with any model endpoint from the list below.
# 1. Submit
curl -X POST https://api.muapi.ai/api/v1/suno-create-music \
-H "x-api-key: $MUAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"an upbeat lofi hip-hop track with mellow piano"}'
# → {"request_id":"abc123","status":"processing"}
# 2. Poll until completed
curl https://api.muapi.ai/api/v1/predictions/abc123/result \
-H "x-api-key: $MUAPI_API_KEY"Top 5 AI Audio Generator Models
| Model | Provider | Cost | Best For |
|---|---|---|---|
| gemini-3-1-flash-tts | — | $0.035 | Gemini 3.1 Flash TTS turns written dialogue into expressive, natural multi-speaker speech with fine-grained control over voice, accent, emotional style, and pace. Ideal for fast, affordable voiceovers, character dialogue, and narration. |
| suno-create-music | — | $0.090 | Suno generate music that turns text prompts into full songs — complete with vocals, lyrics, and instrumentation. You can describe a mood, genre, or even a specific lyric idea, and Suno creates a realistic, studio-quality track in seconds. |
| minimax-speech-2.6-hd | — | $0.650 | Speech-2.6-hd is Minimax’s high-definition text-to-speech model that turns written text into natural, human-like audio. It produces studio-quality speech with clear pronunciation, smooth pacing, realistic emotion, and no background noise. |
| minimax-speech-2.6-turbo | — | $0.650 | Speech-2.6-turbo is Minimax’s fast, lightweight text-to-speech model designed for quick audio generation while maintaining good natural voice quality. It produces clear speech with smooth pacing and minimal delay. |
| elevenlabs-tts-turbo-2-5 | — | $0.050 | Convert text to natural-sounding speech using the ElevenLabs TTS Turbo 2.5 model, with adjustable stability, similarity, and speed. |
All 18 Models
suno-voice-clone
Clone your singing voice in two takes for use with Suno music generation. Submit a 10-second sample, then read back a fresh random phrase the system generates (anti-deepfake liveness check), and receive a reusable voice_id you can drop into Suno music creation. Free during preview.
suno-extend-music
This API extends audio tracks while preserving the original style of the audio track. It includes Suno's upload functionality, allowing users to upload audio files for processing. The expected result is a longer track that seamlessly continues the input style.
mmaudio-v2-text-to-audio
Convert text into natural-sounding speech using mmAudio-v2. Ideal for voiceovers, virtual assistants, and content narration with lifelike clarity and tone.
suno-remix-music
This API covers an audio track by transforming it into a new style while retaining its core melody. It incorporates Suno's upload capability, enabling users to upload an audio file for processing. The expected result is a refreshed audio track with a new style, keeping the original melody intact.
minimax-voice-clone
Minimax Voice Clone creates a high-fidelity digital clone of a speaker’s voice from a short reference audio sample. It reproduces the speaker’s tone, emotion, accent, rhythm, and speaking style, then generates new speech from any text input.
minimax-speech-2.6-hd
Speech-2.6-hd is Minimax’s high-definition text-to-speech model that turns written text into natural, human-like audio. It produces studio-quality speech with clear pronunciation, smooth pacing, realistic emotion, and no background noise.
minimax-speech-2.6-turbo
Speech-2.6-turbo is Minimax’s fast, lightweight text-to-speech model designed for quick audio generation while maintaining good natural voice quality. It produces clear speech with smooth pacing and minimal delay.
suno-add-vocals
Add vocals to an instrumental track.
suno-generate-sounds
Generate sound effects using Suno chirp-crow model.
suno-add-instrumental
Add instrumental backing to acapella audio.
suno-create-music
Suno generate music that turns text prompts into full songs — complete with vocals, lyrics, and instrumentation. You can describe a mood, genre, or even a specific lyric idea, and Suno creates a realistic, studio-quality track in seconds.
elevenlabs-text-to-dialogue-v3
Generate expressive, multilingual text-to-dialogue content using the ElevenLabs Text To Dialogue V3 model.
suno-convert-to-wav
Converts an existing Suno-generated music track to high-quality, uncompressed WAV format for professional editing and processing. Provide the task_id from a prior music generation request and the audio_id of the specific track to convert.
gemini-3-1-flash-tts
Gemini 3.1 Flash TTS turns written dialogue into expressive, natural multi-speaker speech with fine-grained control over voice, accent, emotional style, and pace. Ideal for fast, affordable voiceovers, character dialogue, and narration.
gemini-2-5-pro-tts
Gemini 2.5 Pro TTS is Google's premium text-to-speech model for studio-quality, high-fidelity multi-speaker audio with expressive control over voice, accent, emotional style, and pace.
elevenlabs-tts-turbo-2-5
Convert text to natural-sounding speech using the ElevenLabs TTS Turbo 2.5 model, with adjustable stability, similarity, and speed.
suno-generate-mashup
Create a mashup using 1-5 audio tracks.
minimax-music-3.0
Generate a full song with vocals or an instrumental-only track from a text prompt and structured lyrics with MiniMax Music 3.0.
Frequently Asked Questions
Can I extend an existing track?
Yes — `suno-extend` accepts an audio URL and a continuation prompt and returns a longer clip preserving the original style.
How do I generate audio that matches a video?
Use `mmaudio-v2v` (video-to-audio) — it analyzes the video and generates a matching ambient track or sound effect.