Lyra · Voice & Music
AI audio tools
AI audio tools in this graph: 21, including ElevenLabs, Suno, Whisper, GPT-SoVITS, whisper.cpp and ChatTTS.
Voices, songs, transcripts and clean sound.
Capabilities in this galaxy
Products9
- ElevenLabs2023Lifelike voices, voice cloning and dubbing in dozens of languages.Free plan + paid upgrades
- Suno2023Write a line, get a full song with vocals and instruments.Free plan + paid upgrades
- GPT-SoVITS2024A web UI for cloning a voice from a minute of audio and synthesizing speech with it.Open source, free · Runs offline
- RVC2023A web UI for training voice conversion models on a few minutes of audio and changing voices with them.Open source, free · Runs offline
- Adobe Podcast2022Makes voice recordings sound studio-clean with one click.Free plan + paid upgrades
- Granola2024A meeting notepad that fills out your own notes with the transcript.Free plan + paid upgrades
- Otter.ai2018Live meeting transcription with summaries and action items.Free plan + paid upgrades
- Udio2024High-fidelity music generation with control over each section.Free plan + paid upgrades
- Fireflies.ai2018Joins your calls to record, transcribe and search conversations.Free plan + paid upgrades
CLIs1
Frameworks3
- whisper.cpp2022A dependency-free C/C++ port of OpenAI's Whisper for fast speech recognition on any device.Open source, free · Runs offline
- faster-whisper2023A faster reimplementation of Whisper on the CTranslate2 engine, for transcription.Open source, free · Runs offline
- AudioCraft2023A PyTorch library from Meta with MusicGen and AudioGen for generating music and sound.Open source, free · Runs offline
Models8
- Whisper2022OpenAI's open-weight speech recognition model trained on 680,000 hours of multilingual audio.Open source, free · Runs offline
- ChatTTS2024A text-to-speech model tuned for natural conversational speech in Chinese and English.Open source, free · Runs offline
- Fish Speech2023An open-weight multilingual text-to-speech model family with voice cloning and emotion control.Open source, free · Runs offline
- Chatterbox2025An open text-to-speech model family with zero-shot voice cloning in many languages.Open source, free · Runs offline
- CosyVoice2024A multilingual speech generation model from Alibaba for text-to-speech and zero-shot voice cloning.Open source, free · Runs offline
- F5-TTS2024A text-to-speech model based on flow matching that clones a voice from a short sample.Open source, free · Runs offline
- WaveNet2016DeepMind's generative model of raw audio waveforms that made synthetic speech sound natural.
- ACE-Step2025An open music generation model that writes full songs with vocals from lyrics and a style prompt.Open source, free · Runs offline
Organizations7
- ElevenLabs2022An AI audio company known for realistic text-to-speech, voice cloning and dubbing.
- Suno2022A Cambridge, Massachusetts company that makes the Suno song-generation app and models.
- iFlytek 科大讯飞1999A Hefei company known for speech recognition and synthesis, which also builds the Spark models.
- Otter.ai2016Company that makes Otter, an app for AI meeting transcription and notes.
- Fireflies.ai2016Company that makes Fireflies, an AI notetaker that records and transcribes meetings.
- Granola2023London startup that makes Granola, an AI notepad for meetings.
- Uncharted Labs2023Startup founded by former Google DeepMind researchers that makes the Udio music generator.
Last updated 2026-09-24