Contrapunk – Real-time counterpoint harmony from guitar input
Hi HN, I built Contrapunk because I wanted to play guitar and hear counterpoint harmonies generated in real-time. It takes audio from your guitar, MIDI player or your computer keyboard and generates harmony voices that follow counterpoint rules to generate harmonies. You can choose the key you would like to improvise/play in and the voice leading style and which part of the harmony you would like to play as, as well.macOS DMG: https://github.com/contrapunk-audio/contrapunk/releases/tag/...Source: https://github.com/contrapunk-audio/contrapunk (do open any issues if you have any)Would love feedback on the DSP approach and the harmony algorithms. I am also looking at training a ML model for better realtime guitar to midi detection. I believe that will take some time.
FL score
out of 100
Verdict
high confidence
Competition
12
competitors found, emerging market, funded players
Trend
No signal yet
A real-time counterpoint harmony generator for guitar input, targeting musicians seeking advanced interactive composition and improvisation tools.
The pain
The gap
Build angle
Strengths
- Highly specific and clear problem definition for a passionate niche.
- Unique value proposition not directly addressed by major competitors.
- Strong creator fit, built from personal need.
- Market for AI music tools is large and growing, especially for intelligent assistance.
Risks
- High technical complexity for solo builder (real-time DSP, accurate ML for guitar-to-MIDI).
- Converting an open-source project into a sustainable micro-SaaS business model.
- The niche, while passionate, might be too small for significant revenue without broader appeal.
- Risk of 'AI co-opting' concerns, requiring clear value as an assistive, not replacement, tool.
Next steps
- Gather extensive user feedback from beta testers on GitHub, focusing on musicality and responsiveness.
- Validate pricing strategies with the target audience – what would they pay for enhanced features (e.g., more voice leading styles, improved detection)?
- Focus MVP on perfecting the real-time guitar-to-MIDI detection, as it's critical for the entire experience.
- Explore potential distribution channels and how to reach the niche effectively (e.g., partnerships with music educators, guitar communities).
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 23
- Solution gap
- 19
- Willingness to pay
- 15
- Buildability
- 11
A highly specific, unique music tech idea addressing a creative pain for a niche audience, but faces significant technical challenges in a competitive broader market.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
A promising idea with a clear value proposition in a growing market, but held back by high technical complexity for solo execution and the challenge of establishing a strong moat.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
A well-defined niche problem with strong creator fit and unique angle, but faces challenges in broad audience reach and monetization strategy due to its open-source nature.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
A specific niche product with a clear value proposition and existing technical validation, but needs a clearer business model and further commercial validation to address technical and market assumptions.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Addresses a specific, deep pain for a niche of musicians, with a clear narrow wedge, but needs strong validation on musical quality and robust real-time performance.
Why this verdict
Five lenses, one composite. How scoring works
The angle
This weekend
- Gather extensive user feedback from beta testers on GitHub, focusing on musicality and responsiveness.
- Validate pricing strategies with the target audience – what would they pay for enhanced features (e.g., more voice leading styles, improved detection)?
- Focus MVP on perfecting the real-time guitar-to-MIDI detection, as it's critical for the entire experience.
- Explore potential distribution channels and how to reach the niche effectively (e.g., partnerships with music educators, guitar communities).
Who is already there, emerging market
AIVA is an AI music composition assistant that produces original soundtracks in more than 250 styles without requiring musical training from users.
Pricing: Free tier with attribution; Standard allows limited monetization; Pro grants full copyright ownership. Specific pricing numbers not found in snippets.
Orb Composer is an AI music composition tool designed for composers, bands, and orchestrators to help them experiment with new musical ideas and enhance creativity by generating melodies, rhythm, and harmony.
Pricing: Not specified in snippets, but noted that Orb Producer Suite (a set of plugins by Hexachords, the creators of Orb Composer) is generally more expensive than Scaler.
- ScalerVisit
Scaler is an inspirational MIDI effect that helps users find chords and progressions intuitively, offering note detection, scale selection, and chord suggestions.
Pricing: Scaler 2 is currently priced at $59.99. Scaler 3 is $99.
- Captain Plugins (Captain Chords)Visit
Captain Chords is a song-sketching and composing plugin with an embedded piano roll that helps users manage several song sections and generate chord progressions.
Pricing: Typically more expensive than Scaler, but goes on sale periodically. Specific pricing numbers not found in snippets.
- Amadeus CodeVisit
Amadeus Code is an AI-powered songwriting assistant that helps users make songs in minutes by generating melodies.
Pricing: Not specified in snippets, but some alternatives offer free plans or trials.
- SoundrawVisit
Soundraw is an AI music generator where users can customize aspects like mood, genre, tempo, and instrument to create perfect tracks, offering multiple track variations and an integrated voice synthesizer.
Pricing: Pricing on request.
Beatoven.ai is an AI royalty-free music generator that creates customizable, mood-specific music for various media, offering a composition tool like a digital audio workstation (DAW).
Pricing: Creator plan for 30 minutes/month for $100/year. Unlimited generations on all models, 30 minutes of downloads, advanced track editing. Free tier for 1 Composer model music generation and 1 Maestro music generation per month.
- UdioVisit
Udio is an AI music generator that allows users to create amazing music in their favorite styles with intuitive and powerful text-prompting.
Pricing: Not specified in snippets.
- Suno AIVisit
Suno allows anyone to create music, regardless of skill level, by relying solely on imagination and text prompts.
Pricing: Not specified in snippets.
- Muse AIVisit
Muse AI transforms text prompts into real-time chords, melodies, and basslines with browser and DAW integration.
Pricing: Not specified in snippets.
- AudioCipherVisit
AudioCipher is an easy-to-use MIDI chord and melody generator that turns text into music, helping users overcome creative obstacles.
Pricing: Not specified in snippets.
- HookpadVisit
Hookpad is a modern MIDI composition app that includes melody and chord construction kits, and an AI MIDI generation tool called Aria.
Pricing: $199 outright purchase, or monthly subscription for as little as $7.99.
What they charge
Recent news
- A Review of the Evolution of Music Generation AI in 2024
Medium, January 04 2025
- Magenta RealTime: An Open-Weights Live Music Model
Google AI Blog, June 20 2025
- 48% of artists use AI to make music - fewer than in 2023
Ditto Music, May 20 2025
- The Problem with AI-Generated Music
The Cornell Daily Sun, December 06 2024
- AI-Enabled Text-to-Music Generation: A Comprehensive Review of Methods, Frameworks, and Future Directions
MDPI, March 18 2025
Market signals
The AI music generation market is large and experiencing robust growth. It was valued at approximately $3.2 billion in 2025 and is projected to reach $18.9 billion by 2034, with a CAGR of 21.8%. The AI in music composition SaaS market alone is expected to reach $10.72 billion by 2033, growing at a CAGR of 27.8%. Key trends include increasing demand for AI-powered and intelligent harmonic assistance, real-time harmony generation, user-friendliness, and integration into broader music production ecosystems.
What frustrates people
- Lack of personal creativity offered by AI tools.
- Difficulty with complex user interfaces and learning curves.
- Limited customization options or lower sound quality in free versions.
- Not being able to completely replace human musicality and expression.
- Concerns about AI co-opting and commodifying artists' voices or styles.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “Contrapunk – Real-time counterpoint harmony from guitar input”.