About LyreWave
LyreWave is an all-in-one AI voice studio: it turns text into lifelike speech in 32+ languages, clones voices from short samples, dubs videos into other languages, transcribes audio, and generates music and sound effects — in one workspace, with a developer API. It is free during beta, and no credit card is required.
Free to start
All features free during beta
Languages
32+ (dedicated pages for 12)
Voice cloning
Included, up to 5 voices
Developer API
REST, bearer auth, access on request
Models
Express · Balanced · Premium
Output
MP3 audio; transcripts with timestamps
What LyreWave does
- Text to speech — natural, expressive speech with adjustable stability, similarity, style and speed, across three quality tiers.
- Voice cloning — instant clones from short audio samples, reusable across every tool.
- Video dubbing — translate and dub video into another language while preserving the original speaker’s voice.
- Speech to text — transcription with automatic language detection, word-level timestamps and speaker labels.
- Music & sound effects — original music and cinematic effects from a text prompt.
- Developer API — all of the above over a simple REST API.
Frequently asked questions
What is LyreWave?
LyreWave is an all-in-one AI voice studio. It converts text into lifelike speech in 32+ languages, clones voices from short audio samples, dubs videos into other languages while keeping the original speaker's voice, transcribes audio to text, and generates original music and sound effects — all in one web workspace, with a REST API for developers.
Is LyreWave free?
Yes. LyreWave is free during its beta: every feature — text to speech, the full voice library, instant voice cloning, video dubbing, music, sound effects and transcription — is free to use. Every account starts with 50,000 credits, and no credit card is required. Paid plans are planned after beta for higher volumes.
Do I need a credit card to sign up?
No. You can create an account with just an email address and start generating immediately. No credit card is required to use the free credits.
What languages does LyreWave support?
Text to speech and dubbing support 32+ languages. LyreWave has dedicated pages for 12 of them — English, Chinese, Spanish, French, German, Japanese, Korean, Portuguese, Hindi, Arabic, Italian, Russian — and the same voices can speak across multiple languages.
Can I clone my own voice?
Yes. Instant voice cloning is available to every account during beta. Upload a short, clean recording of a single speaker (30 seconds or more works best), and you can use the cloned voice across text to speech and other tools. Each account can keep up to 5 cloned voices at a time. Only clone voices you own or have explicit permission to use.
Does LyreWave have an API?
Yes. LyreWave offers a REST developer API for text to speech, sound effects, music generation and speech to text, authenticated with a standard bearer token. API access is granted on request: sign in, describe what you're building, and your account is enabled. Requests draw from the same credit balance as the web app.
What audio quality and formats does it produce?
Speech, music and sound effects are delivered as downloadable MP3 files. Text to speech offers three model tiers — Express (fastest), Balanced (low latency) and Premium (highest quality). Transcription returns text with word-level timestamps and speaker labels.
Is LyreWave affiliated with another voice provider?
No. LyreWave is an independent product and is not affiliated with, endorsed by, or sponsored by any other voice or AI provider.
Who is LyreWave for?
Content creators, YouTubers and video producers, podcasters, localization and dubbing teams, educators building courses, and developers who want to add voice generation to their own products through the API.