- Start
- Sep 4, 202690% CONFIDENCEfrom the source
Lyria 3.5 Comes to the Gemini App and Gemini API
- On 4 September 2026 Google made Lyria 3.5, "our best-sounding music generation model", available in the Gemini app and the Gemini API, with "more expressive vocals and richer musical arrangements"[1]
- It is available to all users globally on the web and in the mobile app, as well as in Google Flow Music, Google AI Studio and Google Vids[1]
- Lyria 3.5 first launched in Google Flow Music on 29 July 2026[5][6]
- The Gemini API changelog lists Lyria 3.5 as generally available under 3 September, as lyria-3.5[2]
- In the Gemini app users can pick or describe a genre, choose vocal or instrumental styles, start from templates such as background music or birthday tracks, and choose short or longer tracks[1]
- Safety filters block requests for specific artist voices and copyrighted lyrics; The Next Web notes that a Munich court ruled against Suno on 31 July over memorised works and infringing outputs[5]
Notable features
- Generates full-length songs with verses, choruses and bridges as 44.1 kHz stereo audio, from text prompts or images, with lyrics returned as text[2][3]
- Priced at $0.08 per song on the Gemini API's paid tier[4]
- Accepts up to 131,072 input tokens; developers can supply up to ten images, write their own lyrics with section tags and use timestamps to say when instruments come in[3][5]
- Improved musicality, higher-quality lyrics, more emotionally nuanced vocals with better pronunciation, and control over tempo and duration[6]
- Every track carries an imperceptible SynthID watermark[5]
References 685% CONFIDENCEOverall confidence: 85%How well the pin's source and references back up its dates.Weighted average of how firmly 6 references, the source included, support the pin's start and end times; a reference counts half as much for every 180 days older than the newestShow all pins at 75% confidence or better
The first entry is always the pin's source. Overall confidence is a weighted average of how firmly each reference supports the start and end times used above; a reference counts half as much for every 180 days older than the newest.
- [1]90%blog.google/innovation-and-ai/products/gemini-app/better-tracks-lyria-geminiblog.google· Posted Sep 28, 2026· Starts Sep 4, 2026 ✓· 18% of score
Google's[2][3][4] Keyword post is dated "Sep 04, 2026" and says "Lyria 3.5, our best-sounding music generation model, is now available in the Gemini app and the Gemini API"; The Next Web[5] reported it on 4 September. The Gemini API changelog files the API's general availability a day earlier, under September 3.
- [2]85%Release notes | Gemini APIai.google.dev· Added Sep 28, 2026· 18% of score
The Gemini API changelog entry under September 3, 2026: "Lyria 3.5 generally available (GA)" as lyria-3.5, full-length song generation with improved musical coherence, natural vocals and fine-grained duration and structural control, from text and image inputs at 44.1 kHz stereo.[1]
- [3]90%Lyria 3.5 | Gemini APIai.google.dev· Added Sep 28, 2026· 18% of score
Google's[2][4] model page: lyria-3.5 is "Google's flagship music generation model", takes text and image input up to 131,072 tokens and outputs MP3 audio plus lyrics text; latest update September 2026.
- [4]85%Gemini Developer API pricingai.google.dev· Added Sep 28, 2026· 18% of score
The pricing page lists Lyria 3.5 (Full Song) at $0.08 per song on the paid tier, not available on the free tier, and the older Lyria 3 Clip Preview (30s) at $0.04 per song.[1]
- [5]85%Google brings its Lyria 3.5 music model to every Gemini userthenextweb.com· Published Sep 4, 2026· Starts Sep 4, 2026· 16% of score
The Next Web's same-day report that Lyria 3.5 is in the Gemini app and API for all Gemini users, having first launched in Google[2][3][4] Flow Music on 29 July; it summarises the API documentation (44.1kHz stereo, up to ten images, lyric section tags) and sets the artist-voice and copyrighted-lyrics blocks against the Munich court's 31 July ruling against Suno.
Suggest a correction
Something missing or wrong? Say it in your own words: a link that backs this pin up, a different start or end date and why, or a fact it lacks or gets wrong. The AI checks it against this pin's sources, searches for better ones, and adds any page that backs you up. The pin's own sources still count most. A picture that shows something else, or shows it badly, is looked at too, and moved down or replaced.