Skip to content
SPECIFICTION
Get listed

AudioGen vs FlowSpeech Sound Effects

AudioGen

github.com

FlowSpeech Sound Effects

flowspeech.io

Side by side

FigureAudioGenFlowSpeech Sound Effects
Price fromFree$19/mo
Free planYes—
Free trial——
Open source——
Web—Yes
LinuxYes—
APIYes—
Self-hostedYes—
Plans published14
Spec score · AI Sound Effect Generators8.8 (#2)7.4 (#21)
SupportThe model card directs questions and comments to the project’s GitHub repository or its issue tracker.The sound effects page directs users to contact support at [email protected].

Plans

AudioGen

  • AudioGen (self-hosted)Free

AudioGen pricing →

FlowSpeech Sound Effects

  • Basic$19 a month
  • Pro$59 a month
  • Scale$189 a month
  • FreePrice not published

FlowSpeech Sound Effects pricing →

In their own words

AudioGen

AudioGen is a text-to-sound model provided through AudioCraft. It generates audio samples from text descriptions and can continue from an audio prompt, with conditional and unconditional generation modes. Sampling controls include greedy, temperature, top-K, and top-P methods. The listed pretrained model, facebook/audiogen-medium, has 1.5 billion parameters; the example API generates sound and saves it as WAV. The implementation uses an autoregressive Transformer and a 16 kHz EnCodec tokenizer. The repository provides API access and a local Jupyter notebook demo. Running the medium model locally requires a GPU with at least 16 GB of memory; installation requires Python 3.9 and PyTorch 2.1.0, with ffmpeg recommended. The model was trained on English descriptions and performs less well in other languages. It cannot generate realistic vocals, and prompts may need refinement. Code is MIT-licensed, while weights use CC-BY-NC 4.0; training datasets are not provided. The listed self-hosted plan is free.

Visit github.com

FlowSpeech Sound Effects

FlowSpeech Sound Effects is a freemium web tool that creates sound effects from text prompts and can add effects to video. Prompts can specify intensity, distance, texture and emotion, while users set an exact duration for cuts, loops or transitions. The standard output shown is MP3 at 44.1 kHz and 128 kbps, and each generation costs 2,500 credits. The sound-description field allows up to 450 characters. FlowSpeech describes uses in video, audiobooks, podcasts, games and ads; its page says generated outputs can be used in YouTube videos, podcasts, ads and apps. The Free plan provides 2,000 credits monthly for guests or 10,000 for signed-in users. Paid monthly plans are Basic at $19.00, Pro at $59.00 and Scale at $189.00, each including Gemini TTS API access with shared credits. FlowSpeech says it does not store user data, sends authorized content to a third-party AI platform and advises against entering private information.

Visit flowspeech.io