Audio & speech
ElevenLabs
AI audio platform for text to speech, voice cloning, dubbing, music and voice agents, with a web app and a developer API.
What ElevenLabs does
ElevenLabs generates speech and other audio with its own AI models. Its creative app, ElevenCreative, covers text to speech, voice cloning and voice design, dubbing, sound effects, music, and image and video generation. The homepage says speech is available in more than 70 languages, and Studio projects let you assemble longer pieces such as audiobooks and podcasts.
ElevenAgents is the second product. It is for building conversational agents that answer by voice or text, and the homepage names phone, chat, email and WhatsApp as channels. Agents come with analytics for tracking success rates.
Developers reach the same models through ElevenAPI. The documentation lists official Python and TypeScript SDKs and models including Eleven v4, Eleven v3, Eleven Multilingual v2, Eleven Flash v2.5 and the Scribe v2 speech-to-text family. Every product draws from one monthly credit balance, so a plan's credits are shared between speech, music, sound effects and dubbing.
The free plan is for non-commercial use only, according to the terms of use. Commercial use, instant voice cloning and dubbing start with the Starter plan, and professional voice cloning starts with Creator. ElevenLabs suits creators who need narration or localized voiceovers and developers adding speech or voice agents to a product.
- Narration for audiobooks, podcasts and video voiceovers.
- Dubbing existing video into other languages.
- Cloning a voice or designing a new one from a prompt.
- Building voice or chat agents for customer support.
- Adding text to speech or speech to text to an app through the API.
Who should use it
- Creators who need voiceovers in many languages.
- Developers who want hosted speech models with Python or TypeScript SDKs.
- Teams building phone or chat agents.
Who should look elsewhere
- Commercial projects on the free plan, which the terms limit to non-commercial use.
- Teams that need to run speech models on their own hardware; the official pages describe a hosted service.
Strengths
- One credit balance covers speech, music, sound effects, dubbing and image and video tools.
- Official Python and TypeScript SDKs and a REST API.
- Speech in more than 70 languages.
- Enterprise plans list custom DPA and SLA terms, BAAs for HIPAA customers and custom SSO.
Limitations
- Free plan output may not be used commercially.
- Professional voice cloning needs the Creator plan or higher, and 44.1kHz PCM output through the API needs Pro.
- Usage is capped by monthly credits, so heavy generation pushes you to a higher tier.
- The terms give ElevenLabs a perpetual license to use your content and output to improve its services unless you opt out of training.
Privacy notes
The privacy policy says ElevenLabs may use personal data to train and improve its AI models, and users can opt out in the Data use settings, though the opt-out covers only data provided after it is submitted. It also says voice data it generates is not kept longer than three years after your last interaction, except where the law requires.
Sources
- Free AI Voice Generator & Voice Agents Platform | ElevenLabsOfficial sitePrimaryelevenlabs.io
- ElevenLabs Pricing for Creators & Businesses of All SizesPricing pagePrimaryelevenlabs.io
- Documentation | ElevenLabs DocumentationOfficial docsPrimaryelevenlabs.io
- elevenlabs.io/docs/overviewWeb
- elevenlabs.io/terms-of-useWeb
- elevenlabs.io/privacy-policyWeb
ElevenLabs alternatives
Suno
Audio & speech
AI music generator that makes full songs with vocals from a text prompt or your own lyrics, plus editing tools and a browser DAW.
FreemiumFree tierVerifiedYubi
Audio & speech
Push-to-talk dictation for the Mac that types where your cursor is, plus an AI helper that points to controls on screen.
FreemiumFree tierVerified
Related open-source projects
VoiceStudio is a desktop app that runs speech AI on your own computer: it clones and designs voices, generates speech from text, dubs videos, transcribes audio and has a dictation widget. The app is built on Electron with a Python backend. Its default speech engine is k2-fsa's OmniVoice, and the feature catalog lists more than a dozen alternatives, among them CosyVoice 3, KittenTTS, MLX-Audio and IndexTTS 2.5. Transcription defaults to WhisperX, with Faster-Whisper, Parakeet, Moonshine and others available. Models are downloaded when a workspace first needs them. The project says its tools cover 646 languages, a figure that also appears in the transcription tool of its MCP docs. Beyond the desktop workspaces, VoiceStudio exposes a local API and an MCP server on port 3900, so coding agents can generate speech, clone a voice or transcribe a file. The README states that local workflows stay on your hardware, remote workers are optional and usage analytics only run with consent. Version 0.5.3 was the last release built on Tauri; current releases are Electron only, and Tauri users have to install the new app separately.
- Stars
- 61K
- Language
- Python
- License
- AGPL-3.0
- Momentum
- +16.0% 7dTrending
qwen-audio-agent is a realtime voice runtime that sits in front of a coding or task agent. You talk to a voice model, longer jobs go to a backend agent while the conversation continues, and when a task finishes its result comes back into the same conversation. The voice side is swappable. Cloud options listed in the README include Qwen Audio 3.0 Realtime, GPT-Live / OpenAI Realtime, Google Gemini Live and Doubao Seeduplex 3.0 Realtime, each needing that provider's API key. Hugging Face Speech-to-Speech and MiniCPM-o 4.5 can run locally. Backend agents connect mostly over ACP: the list covers Qwen Code, OpenCode, OpenClaw and Kimi Code, with Codex and Claude Code joining through an external ACP adapter. You can use it from a WebUI, a terminal TUI or a desktop floating orb on macOS, Windows and Linux. The README also lists parallel background tasks you can query or cancel, cross-session memory, and scheduled reminders. The package is published on npm under Apache-2.0, a technical report is on arXiv, and the repository sits in the QwenAudio GitHub organization.
- Stars
- 2.9K
- Language
- JavaScript
- License
- Apache-2.0
- Momentum
- Emerging
iFixAi is an open-source Python tool that audits AI agents and models by running a set of test inspections and returning an A to F grade with a written report. The free engine has 60 inspections. The grade comes from five core pillars: fabrication, manipulation, deception, unpredictability and opacity. Another 28 inspections from twenty premium categories are included and reported on their own, outside the grade. A grade counts as citable only when a judge model from a different vendor scores the run, so a full audit needs two API keys. You can test a bare model through providers such as Anthropic, OpenAI, Gemini, Azure, Bedrock and OpenRouter, or point the tool at your own agent's OpenAI-compatible HTTP endpoint. There are three ways to run it: a setup wizard, a CLI with explicit flags for CI, or a plugin for Claude Code and Codex, with a scaffolded /ifixai-skill command for other agents. Reports land as JSON and Markdown in ./ifixai-results/. The README estimates judge costs for a full run with a Sonnet judge at roughly $12 to $18, billed by the provider. The company also sells iFixAi Pro, a paid audit service with up to 400 inspections. Telemetry is on by default outside CI and can be switched off.
- Stars
- 24K
- Language
- Python
- License
- Apache-2.0
- Momentum
- Established
AI Engineering from Scratch is a free, MIT-licensed course on GitHub that teaches how AI systems work by having you write each piece yourself, starting with linear algebra and ending with multi-agent systems and production infrastructure. The material is split into 20 phases and 523 lessons, with code in Python, TypeScript, Rust and Julia. Each lesson folder holds a written explanation, runnable code and an outputs directory. The pattern is to build an algorithm such as backpropagation, a tokenizer, attention or an agent loop from plain math first, and only then run the same idea through a library like PyTorch or scikit-learn. Lessons end with something you keep: a prompt, a SKILL.md file, an agent or an MCP server. The repository holds 396 skills and 99 prompts produced this way, plus a script that copies them into an agent's skills folder. There are three ways to follow it. You can read lessons on the website with no setup, clone the repository and run the code locally, or install the course's tutor skills into a coding agent such as Claude Code or Codex. Those skills run a placement quiz, write a study plan to LEARNING.md and teach one lesson per session. Separate tracks prepare for the four Claude certification exams and the MCP Associate exam; the README says these are independent and not affiliated with the exam bodies.
- Stars
- 68K
- Language
- Python
- License
- MIT
- Momentum
- +8.2% 7dEstablished