Free music and audio models
Music, speech, and dubbing models confirmed free. For local speech recognition and TTS, see Whisper, Handy, and Kokoro in the software section.
3 models2 providersup to 1M contextUpdated:
Read more
Music APIs more often run on one-time credits than on a recurring free tier.
| # | Model ↕ | AA Index ↕ | GPQA ↕ | Context ↕ | Size ↕ | Free at ↕ | |
|---|---|---|---|---|---|---|---|
| 1 |
Lyria 3 Pro Preview
Google · Audio
|
— | — | 1M | — |  OpenRouter |
|
| 2 |
Lyria 3 Clip Preview
Google · Audio
|
— | — | 1M | — | OpenRouter |
|
| 3 |
OrcaDub 1.0
OrcaDub · Audio
|
— | — | — | — |  OrcaRouter |
No models match your filters.
Benchmarks: Artificial Analysis (September 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.
FAQ
What is the best free model for music and audio?
Lyria 3 Pro Preview currently leads — free at OpenRouter. Next come Lyria 3 Clip Preview, OrcaDub 1.0.