AI Audio API: 18 Models for Music, Speech & Sound

Where to start

Most popularSuno v6suno/v6/text-to-audioFull songs with vocals from your lyrics or a short briefAudioUp to 5 reference imagesYour own lyricsFrom$0.072per run
Lowest priceGrok STTxai/grok-stt/speech-to-textTranscripts with word timings in 25 languagesAudio25 languagesFrom$0.00003per second
NewestGemini 3.8 Flash TTSgoogle/gemini-3.8-flash-tts/text-to-speechExpressive speech that acts out cues like [laughing]Audio70 voicesFrom$0.00032per second

18 models

Suno v6suno/v6/text-to-audioFull songs with vocals from your lyrics or a short briefAudioUp to 5 reference imagesYour own lyricsFrom$0.072per run
Gemini 3.8 Flash TTSgoogle/gemini-3.8-flash-tts/text-to-speechExpressive speech that acts out cues like [laughing]Audio70 voicesFrom$0.00032per second
MiniMax Speech 2.8 HDminimax/speech-2.8-hd/text-to-speechHigh-fidelity speech in 400+ voices with emotion controlAudio472 voices40 languagesFrom$0.12per 1,000 characters
MiniMax Music 3.0minimax/music-3.0/text-to-audioFinished stereo songs, with vocals or instrumentalAudioYour own lyricsFrom$0.18per run
Seed Audio 1.0bytedance/seed-audio-1.0/text-to-audioMulti-voice audio scenes with music and effectsAudioFrom$0.36per run
Gemini 3.8 Flash-Lite TTSgoogle/gemini-3.8-flash-lite-tts/text-to-speechFast, lightweight speech in 30 voicesAudio70 voicesFrom$0.00021per second
Suno v6 Minisuno/v6-mini/text-to-audioTwo quick songs with vocals from one sentenceAudioUp to 5 reference imagesYour own lyricsFrom$0.072per run
Suno v6 Wildsuno/v6-wild/text-to-audioExperimental, textured songs with vocalsAudioUp to 5 reference imagesYour own lyricsFrom$0.072per run
HeartMuLa Transcribeheartmula/transcribe/speech-to-textLyrics pulled from sung vocals, in many languagesAudioFrom$0.05per run
Grok STTxai/grok-stt/speech-to-textTranscripts with word timings in 25 languagesAudio25 languagesFrom$0.00003per second
Grok TTSxai/grok-tts/text-to-speech71 voices across 20 languages with speech tagsAudio71 voices20 languagesFrom$0.018per 1,000 characters
Seed Speech 2.0bytedance/seed-speech-2.0/text-to-speech41 voices with tone set in plain languageAudio41 voices10 languagesFrom$0.072per 1,000 characters
MiniMax Speech 2.8 Turbominimax/speech-2.8-turbo/text-to-speechFast speech in 400+ voices with emotion controlAudio472 voices40 languagesFrom$0.072per 1,000 characters
Qwen3 TTSalibaba/qwen-3-tts/text-to-speechOpen-source speech with tone and pace set in plain wordsAudio9 voices10 languagesFrom$0.068per 1,000 characters
Chatterboxresemble-ai/chatterbox-v1/text-to-speechEnglish speech that can match a short voice sampleAudioFrom$0.036per run
Gemini 2.5 Pro TTSgoogle/gemini-2.5-pro-tts/text-to-speech−10%Directable voices for narration and two-person dialogueAudio30 voicesFrom$0.00045~~$0.0005~~per second
Video Sound Effectspopnow/foley-v1/video-to-audioSound effects and ambience matched to your videoAudio1–30s clipsFrom$0.006for a 5-second clip
Vocal Isolatorpopnow/vocal-isolator-v1/audio-separationNewOne recording, separate voice and background tracksAudioFrom$0.0012per second

By task

Other model types

Browse by maker

Every model maker on PopNow API, with how many of its models you can call.

All model makers

Frequently asked questions

How is AI audio priced?

Speech is usually priced by the amount of text, music and sound effects per track or per second. Each model page lists its unit and every price tier.

Which voices and languages are available?

Each text to speech model lists its voices and languages on its page. Pick a voice by name in the request.

Can I use the audio in my product?

Usage terms follow PopNow's terms of service and any limits of the model you call. Check the model page and the terms before you ship.

AI audio generation API