Completing sign-in

Finishing provider sign-in (or email link). This can take a few seconds on a slow connection.

Sign in to continue

Use the same Supabase account as speaktrue.cc (email, Google, Apple, or the marketing sign-in page).

!
Agreement required Review and accept the Terms of Use before using SpeakTrue.
Review
Checking agreement...

Terms of Use

Review before using SpeakTrue

×

SpeakTrue uses ElevenLabs as a third-party AI speech service. Before any app feature sends your personal data or user content to ElevenLabs, you must review this notice and give permission.

What you are agreeing to

  • You agree to SpeakTrue's Terms of Use and EULA.
  • You acknowledge the Privacy Policy, including the data collection, use, retention, and sharing details.
  • You give SpeakTrue permission to send the feature content you choose to submit to ElevenLabs for AI speech processing.
  • If you do not agree, SpeakTrue's speech, soundboard, voice cloning, and settings features remain disabled until you return here and tap I Agree.

Data sent to ElevenLabs

ElevenLabs is the third-party AI service used for speech processing.

  • Text-to-speech sends the text you enter, selected voice, selected model, and voice settings such as speed, stability, similarity boost, style exaggeration, and speaker boost.
  • Speech-to-text sends the audio recording you choose to transcribe and transcription settings such as model, language, diarization, speaker count, and audio event tagging.
  • Speech-to-speech sends your audio recording for transcription, then sends the resulting transcript text and selected voice settings to generate speech audio.
  • Voice cloning sends sample recordings of your voice, or a voice you have permission to use, so ElevenLabs can create the cloned voice.
  • SpeakTrue also uses Supabase for authentication, database records, edge functions, optional storage, synced settings, and saving this agreement status.

ElevenLabs Privacy Policy

Terms of Use and EULA

You are responsible for the text, recordings, generated speech, cloned voices, and soundboard content you submit or create. Do not use SpeakTrue for unlawful, harmful, abusive, deceptive, impersonation, spam, robocalling, rights-infringing, high-risk, or provider-policy-violating content. SpeakTrue is provided as-is and service behavior may depend on provider availability and network conditions.

Open full Terms of Use and EULA

Privacy Policy

SpeakTrue collects account/session identifiers, submitted text, recordings, voice clone samples, generated/transcribed content, soundboard files and metadata, settings, usage data, and diagnostics only as needed for app functionality, personalization, reliability, and support.

The Privacy Policy identifies what data is collected, how it is collected, how it is used, retention choices, and third parties including ElevenLabs and Supabase. It also states that ElevenLabs provides its own privacy and security protections, and that SpeakTrue relies on those practices to provide the same or equal protection for user content processed by ElevenLabs.

Open full Privacy Policy

Your choice

  • Tap I Agree only if you permit SpeakTrue to transmit the described content to ElevenLabs when you use those features.
  • Tap I Do Not Agree or close this notice to keep all app features disabled. You can reopen this notice from the red bar at the top of the app.
  • You can revoke device permissions such as microphone access in your browser or device settings.

Sign in with email

×

Enter the email and password for your SpeakTrue account.

  • 8–16 characters
  • At least one uppercase letter
  • At least one lowercase letter
  • At least one number
  • At least one symbol

Check your email to confirm your SpeakTrue account, then return here to sign in.

Sign in to enable strict-mode API access
SpeakTrue
Features Pricing FAQ

Text to Speech

Text to Speech Conversion

Character Input Limit: 0 / 10000

Select Voice

Select AI Model

Voice Settings

90%
90%
85%
65%
Warning: Pronunciation prompts are disabled for the selected model.
Processing...
Your browser does not support the audio element.

Text to Speech Instructions

  • Getting Started:
    • Enter your text in the input field above (up to 10,000 characters).
    • Choose your preferred voice from the dropdown - custom cloned voices are marked as "(cloned)".
    • Select an AI model based on your needs:
      • With Pronunciation Control: Use Turbo or Flash models for precise pronunciation control with phoneme tags.
      • Without Pronunciation Control: Use Multilingual v2 for general high-quality speech in multiple languages.
  • Drafts & Recovery:
    • Your edits are autosaved locally every second while typing; the last 50 snapshots are kept.
    • "Save Draft" also posts the current text to the server; background saves occur every 30 seconds during activity.
    • "Recover Draft" opens a history viewer with differences highlighted; restoring never overwrites history.
    • Drafts persist across reloads; recent server drafts are loaded on startup and merged into local history.
  • Voice Settings:
    • Speed: Adjust how fast or slow the speech is delivered.
    • Stability: Higher values create more consistent speech, lower values add more variation.
    • Similarity Boost: Controls how closely the AI follows the original voice characteristics.
    • Style Exaggeration: Amplifies the emotional style of the original voice.
    • Speaker Boost: Enhances clarity and speaker presence.
  • Saving & Conversion:
    • Use "Save to Soundboard" to store the latest TTS result in any folder or category; the saved category refreshes immediately when the Soundboard tab is loaded.
    • Use "Share" when you only need to send the generated audio clip; downloads and shares do not include the associated text file.
    • Pick Format (MP3/WAV/OGG/M4A/MP4), optional Bitrate (lossy only), and Normalize.
    • Defaults for save format/bitrate come from Settings → Default Save Audio Format.
    • After saving, you can Convert any existing clip inside the soundboard to another format; optionally delete the original audio (the text remains attached).
  • Tips:
    • Use the pronunciation glossary in Settings for better results with names, acronyms, and technical terms.
    • Save frequently used audio clips to Soundboard folders, then move, reorder, convert, or combine them from the Soundboard tab.
    • Save style presets in Settings when you find a stability/similarity/speed combination you want to reuse.

Speech to Text Conversion

Upload audio or record your voice to convert to text

Upload Audio

Record Audio (48kHz/24-bit)

00:00

Transcript: (You can edit this text before copying to TTS)

Transcribing... This may take a while depending on the file size.

Speech to Text Instructions

  • Upload Audio:
    • Click "Choose File" to select an audio or video file from your device.
    • Supported formats include MP3, WAV, M4A, MP4, and most common audio/video formats.
    • File size limit depends on provider and file processing limits.
  • Record Audio:
    • Use "Start Recording" to begin capturing audio from your microphone.
    • Recording is high-quality (48kHz/24-bit, 384kbps) for optimal transcription accuracy.
    • Use "Pause" and "Resume" to control recording without stopping completely.
    • Use "Stop" when finished, then save or use the recording directly.
    • You can play back your recording to verify quality before transcribing.
  • Transcription Options:
    • Choose between "Uploaded File" or "Recorded Audio" using the radio buttons.
    • Enable speaker diarization to identify different speakers in the audio.
    • Enable audio event tagging when you want non-speech events captured in the transcript.
    • Select the STT model and language in the tab or set defaults in Settings.
  • After Transcription:
    • Review and edit the transcribed text if needed.
    • Use "Copy to TTS Input" to use the text for speech synthesis.
    • Pronunciation glossary entries from Settings can help normalize custom terms across speech workflows.
    • Download the transcript as a text file for your records.
  • Drafts & Recovery:
    • Transcript edits autosave locally with version history (up to 50 snapshots).
    • "Save Draft" posts the transcript to the server; background saves occur every 30 seconds during activity.
    • Use "Recover Draft" to view recent versions with highlighted changes and restore safely.

Express Speech-to-Speech

Record or upload audio to convert into synthesized speech with your preferred voice

Upload Audio

Record Audio (48kHz/24-bit)

00:00

Select Voice

Select AI Model

Voice Settings

90%
90%
85%
65%
ⓘ
Processing speech-to-speech... This may take a while depending on the file size.

Result:

Your browser does not support the audio element.
Transcribed Text:

Express Speech-to-Speech Instructions

  • What is Express Speech-to-Speech:
    • This feature combines speech-to-text and text-to-speech in one seamless operation.
    • Perfect for voice conversion, accent changes, or speech enhancement.
    • Your input audio is transcribed to text, then converted to speech with your chosen voice.
  • Audio Input:
    • Upload an audio/video file or record directly using the microphone.
    • Choose "Uploaded File" or "Recorded Audio" to select your audio source.
    • Recording uses high-quality settings for best transcription results.
  • Voice and Model Selection:
    • Select your preferred output voice - custom cloned voices show as "(cloned)".
    • Choose an AI model based on your language and quality needs.
    • Adjust voice settings to fine-tune the output speech characteristics.
  • Processing:
    • Click "Process Speech-to-Speech" to start the conversion.
    • The system will transcribe your audio and generate new speech.
    • View the transcribed text and listen to the final result.
    • Use "Copy to TTS" or "Regenerate TTS" for further processing.
    • Share the generated audio by itself, or save it to a Soundboard folder/category for reuse.
    • Use saved style presets and pronunciation glossary entries from Settings to keep repeated conversions consistent.

Soundboard Categories

Open a category directly from this tab. Your clip playback, reorder, combine, and export flows stay in the same in-category panel.

Loading categories...
Unable to load categories right now.
No categories found yet.
Categories come from your Supabase account (for example Saved TTS at saved_tts). Sign in with the same app session, then refresh.

Your Soundboard

Legend: Play Convert Regenerate Move Download Audio Download Text Delete
Move by position Indices match clip order (0 clips)

Moves the clip at the first number into the slot of the second; clips at and below the target shift down. Use Save Order for drag-and-drop changes.


Combine

0 selected

Estimated length: -

Clips
Breaks
Clip Player
Ready

Soundboard Instructions

  • Categories: Managed in Supabase per account (default category "Saved TTS"). Use Load / Refresh after signing in, then create folders, add subfolders, rename, move, delete, or reorder categories from the Soundboard tab.
  • Playing Audio:
    • Click any clip button to play the audio instantly.
    • Use the audio player controls to pause, seek, or adjust volume.
    • Audio plays through the built-in player above the clip list.
  • Managing Clips:
    • Drag and drop clips to reorder them within a category.
    • Use Move by position for precise ordering, then click "Save Order" to persist drag-and-drop changes.
    • Use Restore order when you need to recover a previous clip order snapshot.
    • Select clips with All, None, Invert, Filter, or Range tools before combining.
    • Choose Default gap and Format (MP3/WAV/OGG/M4A/MP4) before combining.
    • Download combined audio and text files for offline use.
  • Adding New Clips:
    • Generate audio in the Text-to-Speech tab.
    • Click "Save to Soundboard" and choose your desired folder or category.
    • New clips appear instantly and are synchronized across browser tabs.
  • Per-Clip Actions:
    • Play the clip, Convert to another format (optionally delete original), Move to another folder (audio and text), Download Audio, Download Text, or Delete.
    • Each saved clip shows when it was saved (from the filename timestamp) so duplicate titles are easy to tell apart.
Quick Access
Settings Sections

Settings

Strict mode: sign in to sync settings with your account.

Speed
75%
Stability
90%
Similarity Boost
85%
Style Exaggeration
65%
Save and reuse Stability/Similarity/Speed/Style/Speaker Boost combinations.
Matches available Speech-to-Text models (same picker semantics as iOS).
Signed-in users sync theme to account; signed-out users save to this browser.

Cache status not loaded.

Saved with your web settings; cached media still depends on browser storage and server cache availability.

Custom terms apply to TTS and STT when a pronunciation entry exists. Entries are stored in your app database (same as iOS/Android glossary).

    Settings Instructions

    • Quick Access: manage pronunciation glossary entries that sync with mobile.
    • Text-to-Speech: defaults apply to the TTS tab, soundboard save, combine flows, and reusable style presets.
    • Speech-to-Text: defaults apply to STT model, language, diarization, speaker count, and audio event tagging.
    • Theme: choose a sampler button to preview colors before saving; signed-in users sync the selected theme to their account.
    • Soundboard: manage folders, subfolders, saved clips, ordering, combining, conversion, and sharing in the Soundboard tab.

    Voice Cloning

    Create custom voice clones from your audio samples using AI technology

    My Custom Voices

    Loading your custom voices...

    Create New Voice Clone

    Step 1: Upload Voice Samples

    Upload 1-10 high-quality audio samples (MP3, WAV, M4A). For best results, use clear speech samples totaling 1+ minutes.

    Drag and drop audio files here

    or

    Uploaded Files:

    Step 2: Configure Voice

    Default Voice Settings
    90%
    85%
    Clone Preflight

    Run sample-quality checks before creating your clone (same backend preflight used by iOS/Android).

    Preflight not run yet.

      Processing...

      Instructions

      • Voice Cloning:
        • Upload 1-10 high-quality audio samples of the voice you want to clone.
        • For best results, use clear speech samples totaling at least 1 minute.
        • Supported formats: MP3, WAV, M4A, and OGG files.
        • Enter a unique name and optional description for your voice clone.
        • Confirm you have rights and consent before samples are sent for voice cloning.
        • Run preflight to check sample quality before creating the clone; fix blockers shown in the checklist first.
        • Adjust the stability and similarity settings to fine-tune the voice characteristics.
        • Click "Create Voice Clone" to process your samples with AI technology.
        • Once created, your custom voice will appear in the voice selection dropdown across all tabs.
      • Managing Custom Voices:
        • View all your custom voices in the "My Custom Voices" section above.
        • Use the "Preview" button to test how your voice clone sounds.
        • Use "Refresh" to reload clones after creation or account changes.
        • Delete voices you no longer need with the inline delete confirmation.
        • Custom voices are marked with a special indicator in voice selection dropdowns.
      • Tips for Best Results:
        • Use high-quality audio recordings with minimal background noise.
        • Read the guided recording scripts on mobile when you need more natural pacing, rhythm, and tone.
        • Include varied speech patterns and emotions in your samples.
        • Longer audio samples (1-3 minutes total) generally produce better voice clones.
        • Speak clearly and at a consistent volume across all samples.
        • Avoid music, sound effects, or multiple speakers in your audio files.

      Save to Category

      ×

      Select a category to save the clip to:

      Bitrate applies to mp3/ogg/m4a/mp4. wav ignores bitrate.