Lyria 3.5 takes 131,072 tokens; Sume music prompts, 5,000 chars
Google lists a 131,072 token input limit for Lyria 3.5. Sume's music prompt field takes 1 to 5,000 characters. What fits and how to trim.
Sume's music prompt is limited to 1 to 5,000 characters, far below the 131,072-token input limit Google lists for Lyria 3.5 on its model page (read 2026-10-01). Through Sume, the 5,000-character cap is the one that applies.
What does Google list?
The model page gives id lyria-3.5, text and image input, MP3 audio and lyrics text output, a 131,072 input token limit and 44.1 kHz stereo.
| Item | Lyria 3.5 (Google) | Sume Music Router and Music 1.0 |
|---|---|---|
| Input limit | 131,072 tokens | Prompt of 1 to 5,000 characters |
| Unit to count | Tokens | Characters |
What does that mean on Sume?
The Music Router and Music 1.0 take prompt 1 to 5,000 characters, so a very long lyric sheet may not fit. Over the limit, trim: keep section tags, drop repeated choruses, and say a chorus repeats instead of writing it out. Count characters before you send, not tokens.
What should the prompt hold?
Mood, genre, tempo, key, instruments and arc, then the lyrics. The docs treat directions as guidance.
Sources
Related posts
More in Models
- Lyria 3.5 takes up to 10 images; Sume music takes one image_url
Google's Lyria guide allows up to 10 images as input. Sume's music docs describe one optional public HTTPS image_url. What that changes.
- MAI-Transcribe-2 languages (60) vs Sume STT language hint
Microsoft's MAI-Transcribe-2 preview covers 60 languages. Sume STT 1.0 takes one optional language_code hint and auto-detects when you omit it.
- MAI-Transcribe-2 speaker diarization vs Sume STT: no speaker field
MAI-Transcribe-2 attributes each segment to a distinct speaker. Sume STT has no diarize field: provider knobs are fixed server-side and you get words[].
- Midjourney edit model image references: 4 vs Sume's ranges
Midjourney's V8.2 edit model takes up to 4 image references. On Sume the ceiling is per model: GPT Image 2.5 takes up to 16. Read the descriptor first.
Written by Sume