---
type: "post"
id: "jasco-adds-flow-matching-text-to-music-with-052f26"
slug: "jasco-adds-flow-matching-text-to-music-with-052f26"
title: "JASCO adds flow-matching text-to-music with chord, drum and melody timing conditions."
description: "**Thesis:** JASCO makes text-to-music generation more controllable by combining a global prompt with timed musical conditions."
retrieval_nugget: "**Thesis:** JASCO makes text-to-music generation more controllable by combining a global prompt with timed musical conditions."
published_at: "2026-10-16"
updated_at: "2026-10-16"
record_date: "2026-10-16"
date_kind: "published_at"
topics: ["generative-media","models"]
source_urls: ["https://github.com/facebookresearch/audiocraft/blob/main/docs/JASCO.md"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:jasco-adds-flow-matching-text-to-music-with-052f26"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:641669b8e892b114b071b31be5785b79171cd54183e5d9970974fa0ce3ad2da4","reviewed_at":"2026-10-16T03:00:13.440Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"JASCO makes text-to-music generation more controllable by combining a global prompt with timed musical conditions.","observed_facts":[{"text":"AudioCraft documents four pretrained JASCO variants: 400M and 1B models with chord and drum support, and 400M and 1B models that add melody support.","source_urls":["https://github.com/facebookresearch/audiocraft/blob/main/docs/JASCO.md"]},{"text":"The documentation says the models generate 10-second samples and shows chord inputs with timestamps.","source_urls":["https://github.com/facebookresearch/audiocraft/blob/main/docs/JASCO.md"]},{"text":"The project provides an API, a local Gradio demo, and a Jupyter notebook.","source_urls":["https://github.com/facebookresearch/audiocraft/blob/main/docs/JASCO.md"]}],"mechanism":"AudioCraft describes a flow-matching model that accepts text descriptions alongside local conditions such as chord progressions, drums, and melody.","why_now":"The repository documents pretrained models, an API, and local demo paths, so the controls are presented as an implementable workflow rather than only a research concept.","implications":["Builders can explore music generation where arrangement constraints accompany the prompt, rather than relying on text alone.","Timed controls offer a specific interface for prototyping structured musical workflows."],"evidence_boundary":"The supplied documentation verifies what the project exposes, but does not establish a release date, independent quality results, licensing details beyond the stated use of roughly 16,000 hours of licensed music for training, or commercial readiness.","watch_conditions":["Watch for independent evaluation of whether the timed conditions reliably shape generated samples and how well the workflow performs on user-provided material."],"related_records":[],"new_branch_reason":"This starts a distinct analytical record because no prior New Runtime record for this specific JASCO capability was supplied."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/jasco-adds-flow-matching-text-to-music-with-052f26/","markdown":"https://newruntime.com/posts/jasco-adds-flow-matching-text-to-music-with-052f26.md","json":"https://newruntime.com/posts/jasco-adds-flow-matching-text-to-music-with-052f26.json"}
related_patterns: ["generative-media-becomes-application-infrastructure"]
---

# JASCO adds flow-matching text-to-music with chord, drum and melody timing conditions.

## Retrieval answer

**Thesis:** JASCO makes text-to-music generation more controllable by combining a global prompt with timed musical conditions.

**Thesis:** JASCO makes text-to-music generation more controllable by combining a global prompt with timed musical conditions. **Mechanism:** AudioCraft describes a flow-matching model that accepts text descriptions alongside local conditions such as chord progressions, drums, and melody. **Why now:** The repository documents pretrained models, an API, and local demo paths, so the controls are presented as an implementable workflow rather than only a research concept.

The source lists four pretrained variants: 400M and 1B models with chord and drum support, and 400M and 1B models that add melody support. It says these models generate 10-second samples, and its example supplies chords with timestamps. **First implication:** Builders can explore music generation where arrangement constraints accompany the prompt, rather than relying on text alone. This is a useful design surface for prototyping structured musical workflows.

**Evidence boundary:** The supplied documentation verifies what the project exposes, but does not establish a release date, independent quality results, licensing details beyond the stated use of roughly 16,000 hours of licensed music for training, or commercial readiness. **First watch condition:** Watch for independent evaluation of whether the timed conditions reliably shape generated samples and how well the workflow performs on user-provided material. This starts a distinct analytical record because no prior New Runtime record for this specific JASCO capability was supplied.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Generative Media](https://newruntime.com/topics/generative-media.md): Explore the generative-media topic hub.
- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)