Features

Read, listen, and produce. All in one place.

EchoLive turns documents, feeds, and videos into high-quality audio — with a production studio (segment editing, SSML, exports) and a listening inbox (feed reader, organization, AI search) so you can listen, refine, and publish.

Who it's for

One platform, many ways to use it

EchoLive serves readers who want all their sources in one place, listeners who want to hear everything, and creators who need production control.

Listeners

Your personal content library

Subscribe to feeds, save articles, and organize everything in one place. Listen with natural voices whenever you want, or just read.

  • Quick Read: paste any text, get audio in seconds
  • Feeds: RSS, newsletters, podcasts, and YouTube in one inbox
  • Podcast transcription & AI summaries for key takeaways
  • AI Search across your entire saved library
Power readers

All your sources, one inbox

Stop checking 20 different sites. Subscribe to RSS feeds, newsletters, podcasts, and YouTube channels in one place, then read or listen on your terms.

  • RSS, newsletters, podcasts, and YouTube in a single feed reader
  • OPML import: migrate from Feedly, Inoreader, or any reader in one step
  • Folders, filters, and sorting to organize high-volume sources
  • Reader mode, AI search, and optional audio generation
Students

Study by listening

Import documents, keep them structured, listen on the go, and search what you have saved.

  • Import PDF, DOCX, Markdown, HTML, and URLs
  • Word-sync read-along highlights as it plays
  • Semantic search across projects and feed items
Creators

Produce audio from scripts

Full studio control with per-segment voices, SSML, iteration, and exports for publishing.

  • Studio editor with per-segment voice, style, and pacing
  • Segmented waveform navigation and generation controls
  • Export MP3, WAV, and production bundles (ZIP/AAF)
Educators

Turn lessons into audio

Consistent voice delivery for course materials with fine control over pacing and emphasis.

  • Segment-based structure for lessons and chapters
  • Voice presets to keep delivery consistent across sessions
  • Smart Import with AI-assisted segmentation and pacing
Authors

Narrate long-form content

Handle book-length scripts with professional controls for pronunciation, pauses, and structure.

  • Visual SSML editor for prosody, emphasis, and breaks
  • Long-form generation with progress tracking
  • Production exports for downstream editing and publishing

Listen

Your personal content library

Feeds for reading and organizing, Quick Read for instant audio, AI Search for finding anything later. All connected by one persistent player.

Quick Read

Paste text, pick a voice, get audio. Plays globally across the app. Word-level sync highlights text as it plays.

Feeds inbox

A full feed reader for articles, podcasts, newsletters, and YouTube with folders, filters, auto-refresh, OPML import, and audio generation.

Podcast transcription

Auto-transcribe podcast episodes and generate AI summaries. Get the highlights without listening to the full episode.

Feed discovery

Semantic search and a curated category browser to find new feeds. Describe what you want and subscribe in seconds.

AI Search

Semantic vector search across your entire library, spanning feeds and projects, so saved content stays discoverable.

EchoLive feeds dashboard showing subscribed RSS feeds and articles with audio status
Feeds dashboard with subscriptions and audio status
Article reader view with full text and integrated audio player
Article reader with audio playback
AI-powered semantic search results across feeds and projects
AI Search across your entire library
Single feed view showing all articles from one subscription
Single feed view with article list

Create

Studio-grade audio from text

A full segment editor with per-section voice control, SSML tools, smart import, and exports for real production workflows.

Studio editor

Multi-segment timeline with per-segment voices/styles, visual SSML tools, and a segmented waveform for fast navigation.

Smart Import

Import txt/md/docx/pdf/HTML/URLs and auto-segment with optional AI-assisted comprehension to improve structure and pacing.

Exports

Export MP3/WAV, ZIP bundles, and AAF-style packages for production workflows and downstream editing.

EchoLive Studio editor in unified text view with all segments
Studio editor: unified text view
Studio segment view with per-segment voice control and settings panel
Per-segment voice control and settings
Visual SSML editor with element list, emphasis, breaks, prosody controls
Visual SSML editor with fine-grained control over breaks, emphasis, prosody, and pronunciation

Shared

Foundations that power both sides

Whether you're listening or creating, these core capabilities are always available.

630+ neural voices

Azure Speech's full voice catalog with previews, search, filters, favorites, presets, and per-context defaults.

Light & dark mode

Light, dark, and system themes that follow your OS preference. Persistent across sessions with no flash.

Credits billing

Pay-as-you-go credits with cost estimation and refunds on failures/cancels. Subscription billing is planned.

Voice library with 630+ neural voices, filters, and previews
630+ neural voices with search and previews
Projects list showing saved studio projects with audio status
Projects: your saved studio work

All features

Everything that ships today

The full list of functional capabilities available in EchoLive right now.

  • Secure sign-in and private, account-scoped content.
  • Leverages Azure Speech’s large voice catalog (availability varies by locale).
  • Voice previews, search, filters, favorites, and presets to choose voices quickly.
Core surfaces (the product “modes”)
  • Quick Read: paste text → generate audio quickly (single job).
  • Studio: multi-segment timeline editor for production workflows.
  • Feeds: RSS/Atom + crawl-based “inbox” for articles/podcasts/newsletters (with optional YouTube channel support).
  • Library: browse/organize voices, favorites, collections, and presets (synced).
  • Projects: manage saved work and play/export long-form outputs.
Global playback (cross-app)
  • A single persistent player used across the app for:
    • Quick Read audio,
    • Studio segment playback,
    • merged project playback,
    • feed-item audio playback,
    • YouTube playback mode (separate from TTS audio).
Quick Read (single-pass generation)
  • Voice selection (simple + advanced voice modes) with styles, rate, pitch, and volume controls.
  • Optional SSML input mode.
  • Real-time generation progress with job resumption after refresh.
  • Word-level highlighting view when timing data is available.
  • Global persistent playback (doesn’t stop when navigating to other pages).
  • Primary and secondary Quick Read actions (Generate, Download MP3, Open in Studio) follow consistent UX styling.
Studio editor (multi-segment projects)
  • Segment-based timeline (text segments + pause segments).
  • Per-segment voice settings: voice, style, rate, pitch, volume, SSML vs plain text.
  • Batch operations: reorder, select many, bulk delete, collapse/expand, “apply settings to all”.
  • “Unified Text View”: edit all segment text in one continuous editor with non-editable segment markers.
  • Focus mode for distraction-free editing.
  • Segment-level generation: generate, regenerate, cancel, play-while-generating.
  • Project-level Word Sync toggle (controls whether word-level timing is generated/used).
  • Segment waveform timeline (“segmented waveform”) for fast navigation/seek to a specific segment/time.
  • Per-segment visual SSML editor (build SSML with UI for breaks, emphasis, prosody, say-as, phonemes, substitutions) + manual SSML editing.
Import (documents → segments)
  • Import formats:
    • Timeline JSON (.json) project imports/exports.
    • Text/Markdown (.txt, .md) with formatting preservation for emphasis.
    • PDF (.pdf) via client-side extraction (PDF.js).
    • Word (.docx) with formatting/headings (mammoth.js → Markdown).
    • HTML/Google Docs export (.html, .htm, .gdoc).
    • URL import (“reader mode” extraction via backend).
  • Segmentation strategies:
    • Automatic detection (best strategy per document).
    • Markers (e.g. ---SEGMENT---, <!-- SEGMENT -->, ===).
    • Headings (H1/H2 hierarchy splitting).
    • Paragraph splitting and length-aware fallback splitting.
AI-assisted import & comprehension
  • Adaptive Comprehension Mode / Smart Import: AI analyzes text complexity and suggests:
    • better segment boundaries,
    • pacing adjustments,
    • optional pauses,
    • style suggestions,
    • “emphasis” candidates.
  • Asynchronous job model with progress and result retrieval.
Voice library & personalization
  • Azure voice discovery (/api/voices) and caching.
  • Voice preview library and preview sync/status tooling.
  • Voice Library UI:
    • search + filters (locale, gender, styles),
    • favorites,
    • collections,
    • presets (voice + style + prosody),
    • default voices per context (quick_read, feeds, studio) synced across devices.
Projects (management + playback)
  • Projects list with search and sorting.
  • Project folders with customizable colors and sort order for organizing saved work.
  • Color-coded project tags for cross-cutting labels and filtering.
  • Rename, delete, multi-select operations.
  • "Prepare audio" for project playback (merge segments into a single playback file when needed).
  • Auto-save / draft tracking behaviors in the Studio lifecycle.
Export (Studio → files)
  • Export types:
    • Audio (MP3/WAV).
    • Timeline JSON (project data).
    • Segment bundles (ZIP of per-segment assets, when applicable).
    • AAF bundle (ZIP containing an AAF-like XML + audio assets for import into editors).
  • Export job history with progress tracking, downloads, and cleanup.
Feeds (content inbox)

EchoLive Feeds is a full feed reader + ingestion system, not just an “RSS importer”.

  • Subscribe/import:
    • RSS/Atom feed discovery from a website URL (handles direct-feed URLs).
    • Crawl-based "feeds" for non‑RSS sites (discover URLs and import selected pages).
    • Sitemap parsing for bulk URL discovery.
    • OPML import: batch import subscriptions from Feedly, Inoreader, NetNewsWire, or any other feed reader (supports OPML 1.0/1.1/2.0 with nested folder/category preservation).
    • Curated recommendations and categories.
  • Feed categorization:
    • Feed-level category (article | podcast | newsletter) with user override.
    • Item-level content type (article | podcast_episode | newsletter).
    • Podcast items play enclosure audio (no TTS); newsletters force TTS behavior.
  • Feed settings:
    • folder organization,
    • fetch interval,
    • auto-generate audio (default voice),
    • cleanup patterns (preview/apply to remove repeated boilerplate).
  • Items:
    • pagination, sorting, date filters,
    • search (title/excerpt/author),
    • read/unread, starred, bulk delete,
    • edit publication dates (single + bulk mappings).
  • Reader experience:
    • full-screen Article Viewer (reading view) with font size controls,
    • refresh/re-fetch item content,
    • in-view audio controls + generation controls,
    • word-sync overlay for “read along” playback when timing is available.
  • Audio for items:
    • per-item generate/regenerate/cancel with progress,
    • bulk generation with rate-limited queueing,
    • sticky player with seek + playback speed,
    • playback position persistence to backend.
  • Scheduled refresh:
YouTube support in Feeds (Shipped; API key optional)
  • Subscribe to YouTube channels via:
    • RSS conversion when available, and/or
    • YouTube Data API browsing (optional YOUTUBE_API_KEY) to go beyond typical RSS limits.
  • Browse/search channel videos, import selected videos into a feed.
  • Transcript + summary pipeline (optional):
    • fetch transcripts when available,
    • AI summarization,
    • optional summary-to-audio generation.
  • YouTube playback mode in the global player (separate from TTS audio playback).
Podcast transcription & summaries (Shipped)
  • Auto-transcribe podcast episodes via speech-to-text when auto_transcribe_summarize is enabled on a feed.
  • AI summary generation from episode transcripts: concise takeaways without listening to the full episode.
  • Transcript and summary language preferences (per-user).
  • Quota-managed transcription per user tier.
  • Combined with YouTube transcription, forms a unified transcript + summary pipeline across audio/video content.
Feed discovery (Shipped)
  • Semantic search-powered feed discovery: describe a topic in natural language and get validated RSS/Atom feed results ranked by relevance.
  • Category-based wizard browser with progressive drilling into subcategories.
  • Pre-seeded catalog of popular feeds across dozens of categories.
  • Geographically personalized recommendations (country, region, city, timezone).
  • Bulk subscribe from discovery results with per-batch configuration (voice, refresh interval, category).
Notifications
  • In-app notification center backed by the database.
  • Notification actions for common flows (e.g., retry from “insufficient credits” events).
Billing & tier system

Credits (prepaid, pay-as-you-go)

  • Credit-based prepaid billing model:
    • cost estimation by text length,
    • reserve credits on job start,
    • confirm on success,
    • refund on failure/cancel.
  • Transactions + usage history.
  • Coupons (validate/redeem) and admin tools for managing credits/coupons and cleanup/backfills.
  • Credit expiry: each purchase/grant expires 365 days from its date; the quota API reports credit_expiry (earliest expiry, credits expiring soon).

Lifetime tiers (permanent, earned via cumulative spend)

  • Tier is derived from lifetime_purchased (total credits ever purchased/granted). Once earned, a tier never decreases (ratchet model).
  • Tiers (in order): FreeBetaPaidStarter (350K) → Creator (2M) → Professional (6M) → Producer (15M) → Enterprise (30M).
  • Each tier defines: quotas (AI search/day, feeds, imports/exports, concurrent jobs, etc.), resource limits (max chars/request, max projects, max voice presets, etc.), and feature unlocks (boolean flags like hd_voices, studio_access, ssml_editing).
  • Tier definitions live in config/tiers.json — the single source of truth. All backend modules derive constants from this config.
  • Admin plan assignments can override tier-derived plans for specific users (e.g., granting Enterprise features to a beta tester).

Credit packs (credits only, no feature unlock)

  • Five fixed-price packs: Lite ($5, 65K), Plus ($10, 150K), Value ($20, 350K), Premium ($50, 1M), Ultra ($100, 2.2M).
  • Each pack includes ~25% bonus credits. All credits count toward lifetime_purchased for tier progression.
  • Pack names are deliberately different from tier names to avoid implying a single purchase unlocks that tier.

Feature bundles (credits + 12-month feature access)

  • Three fixed-price bundles: Essentials ($35, 350K credits, Creator-tier features), Pro Tools ($75, 1M credits, Professional-tier features), Studio Suite ($150, 2.2M credits, Producer-tier features).
  • Bundle features are temporary (365 days from purchase). Credits are permanent and count toward lifetime_purchased.
  • Bundle names describe the feature set (not the tier level) to avoid confusion with tier names.
  • Multi-bundle cascade: users can hold multiple active bundles. The highest-tier bundle's features apply; when it expires, features fall back to the next-highest active bundle; after all bundles expire, features revert to the user's permanent lifetime tier.
  • Plan resolution: effective features = MAX(tier-derived plan, highest active bundle). Features use OR (true wins), limits use MAX of both.

Tier-gated quotas and features

  • Quotas are rate-limited counters (per-day or per-month) that reset automatically: ai_search, ai_comprehension, imports, exports, feeds, free_credits, feed_suggestions, auto_generations, ai_summary.
  • Resource limits are static caps tied to the effective plan: max_chars_per_request, concurrent_jobs, max_active_projects, max_segments_per_project, max_feeds, max_feed_folders, max_youtube_channels, max_newsletters, max_voice_collections, max_voice_presets, max_auto_refresh_feeds, auto_generations_per_day.
  • Feature unlocks are boolean flags: hd_voices, studio_access, extended_ai_quotas, auto_refresh, all_voice_styles, wav_download, youtube_subs, ssml_editing, word_timing, newsletter_ingestion, content_cleanup_full, aaf_export, timeline_export, ai_summaries, segments_zip_export.

Free trial

  • New users receive a 14-day free trial with 5,000 credits and Producer-tier features (configurable in config/tiers.json under free_trial).

Subscription billing

  • Subscription billing is planned (Phase C); current model is pay-as-you-go via credit packs and feature bundles.
Global AI Search (Shipped)
  • Ingest → index → vector search pipeline over your own content:
  • UI:
    • Cmd/Ctrl+K global search modal with keyboard navigation,
    • filter chips (All / Feeds / Projects).

Trust

Private, reliable, and secure

Your content stays private. Long jobs stay reliable. Access stays protected.

Isolated by design

Each account has its own dedicated database. Your projects, feeds, and search index are isolated from every other user, not just filtered by permission.

Encrypted at rest

Project text, AI comprehension data, and sensitive metadata are encrypted before storage. Your content is protected even at the infrastructure level.

No content logging

Your text and audio are never logged or used for training. Client monitoring redacts sensitive fields by default. You own your content.

Reliable long-form generation

Background processing with progress tracking, automatic retries, and resumable sessions. Long scripts generate reliably without losing your place.

Secure access

Modern authentication protects access across devices. Provider credentials are managed server-side and never exposed to the client.

Data control

Full data export and account deletion endpoints available. Your data is yours to keep or remove at any time.

Next

What we're building toward

Areas we're actively exploring, shaped by how listeners and creators use EchoLive.

Studio & production workflows
  • Pronunciation dictionary (per account/project), phoneme tooling, and reusable style/preset packs.
  • Audio enhancement: background music mixing, fades/crossfades, loudness normalization/mastering.
Studio & production workflows
  • Pronunciation dictionary (per account/project), phoneme tooling, and reusable style/preset packs.
  • Audio enhancement: background music mixing, fades/crossfades, loudness normalization/mastering.
  • Collaboration: sharing, team workspaces, comments, version history.
  • Integration/export expansion: richer DAW/video editor interchange, webhooks, public API.
Voice capabilities
  • Voice cloning / custom voices (subject to provider constraints and policy).
  • Multi-speaker scripting improvements and automated “role casting”.
Mobile
  • A mobile-first companion app focused on capture + offline listening (not a web wrapper):
    • camera/OCR → TTS,
    • share-sheet URL/article import,
    • background audio + downloads,
    • CarPlay/Android Auto,
    • lightweight editing + sync.
AI features
  • More advanced summarization and “listenability” transformations (e.g., newsletter → concise audio brief).
  • Semantic navigation and highlights over long audio (“jump to section”, “key points”).

Comparisons

How EchoLive compares

EchoLive sits at the intersection of listening apps and production tools. Here's how the features compare.

Quick comparison

This chart reflects typical product focus and may not capture every feature or tier.

Capability EchoLiveFeed readers (Feedly, Inoreader)SpeechifyElevenLabsDescript
RSS / Atom feed reader
Newsletters, podcasts, YouTube in one inbox RSS only (some paid)
Folders, filters, auto-refresh
OPML import (migrate subscriptions) ✓ (OPML 1.0/1.1/2.0 with folders) Export only
Generate audio from any feed item ✓ (one click or bulk) Paste URL only
Podcast transcription & AI summaries ✓ (auto-transcribe + summary) ✓ (transcription)
Instant paste-to-audio (Quick Read)
Article reader mode (free, no credits) Subscription
Semantic AI search across library Keyword only Limited
Long-form production (segment/timeline editing) Limited ✓ (audio-first)
Visual SSML tools Limited
Large voice catalog (630+) ✓ (Azure) Limited
Smart Import (PDF/DOCX/MD/URL) URL/paste only Audio import only
Production exports (MP3/WAV/ZIP/AAF) Basic Basic
Pay-as-you-go credits Subscription only Subscription only Credits + subscription Free / paid tiers
Compared to feed-first platforms (e.g. Feedly, Inoreader)

Feed readers like Feedly and Inoreader are great at RSS aggregation. EchoLive is also a full feed reader, but it adds audio generation, AI-powered search, and a production studio on top.

  • Same core feed reading: RSS/Atom, folders, filters, read/unread, starring, auto-refresh. EchoLive also supports newsletters, podcasts, and YouTube channels natively.
  • OPML import: Migrate your entire subscription list from Feedly, Inoreader, or any other feed reader in seconds. EchoLive parses OPML 1.0/1.1/2.0 files and preserves your folder structure.
  • Article reader (free, no credits): Built-in reader mode with font controls and read/unread tracking. Reading is always free.
  • Podcast transcription & summaries: Auto-transcribe podcast episodes and generate AI summaries. Get key takeaways without listening to the full recording. Feed readers don't offer audio intelligence.
  • Feed discovery: Find new feeds with semantic search or browse curated categories with geographic personalization. No more hunting for RSS URLs manually.
  • Audio from any item: Generate audio from any feed item with one click, or bulk-generate across a feed. Feed readers have no audio capability.
  • Semantic AI search: Vector search across your entire library (feeds and projects). Feed readers typically offer keyword search only, with AI features locked behind higher-tier plans.
  • Production studio: When you need more than a quick listen, move content into Studio for per-segment voice control, SSML, and production exports. No equivalent in feed readers.

If you use a feed reader today and wish it could also read content aloud, search semantically, or produce audio for sharing, EchoLive replaces the feed reader and adds everything else.

Compared to voice-first platforms (e.g. ElevenLabs)
  • EchoLive is workflow-first: timeline/segment editing, bulk regeneration, exports, and long-form project management.
  • EchoLive is ingestion-first: built-in feeds (RSS/crawl/newsletters/podcasts) and optional YouTube channel workflows — a full listening layer, not just a generation API.
  • EchoLive is provider-leveraging: built around Azure Neural TTS (breadth of voices, regional availability) rather than proprietary voice models.
  • Voice cloning/custom voice creation is not currently the core shipped differentiator (it’s a possible roadmap item).
Compared to feed-first platforms (Feedly, Inoreader)
  • EchoLive goes beyond reading: generate audio for any feed item, auto-transcribe podcasts, and get AI summaries — features no traditional feed reader offers.
  • OPML import makes migration seamless: import your entire subscription list with folder structure preserved (supports OPML 1.0/1.1/2.0).
  • Podcast transcription & summaries: auto-transcribe podcast episodes and generate AI summaries — get key takeaways without listening to the full recording.
  • Feed discovery: find new feeds via semantic search or a curated category browser with geographic personalization.
  • AI Search across your entire library turns saved content into a searchable knowledge base.
Compared to consumer "read it to me" apps (e.g. Speechify)
  • EchoLive serves both listeners and creators — it's not only a playback app but also a full production studio.
  • EchoLive has production controls (SSML, per-segment voices, AAF exports) that are typically out of scope for consumer readers.
  • EchoLive's Feeds model supports mixed media (articles + podcasts + YouTube) with unified playback and generation pipelines — plus OPML import, podcast transcription, and AI summaries.
  • EchoLive adds semantic search over your own library (ingest → index → vector search), which turns "saved content" into a searchable knowledge base.
Compared to traditional audio editors (e.g. Descript)
  • EchoLive generates high-quality audio from text with TTS-native controls and then can export to editing workflows (e.g., AAF bundle).
  • EchoLive is not primarily a recorded-audio editor; it’s optimized for script → voiced audio pipelines.