Google-only workspace
This page filters the voice list to Google Cloud voices only, so you can compare variants without mixing providers.
Google Cloud Text to Speech on TTSForge
A focused workspace for Google-only voices, advanced SSML editing, and faster iteration.
Write SSML only, insert tags from a focused toolbar, validate your markup, and generate downloadable audio without leaving the page.
TTSForge / Google
Google Cloud Text to Speech
Convert SSML into speech with precise control over pauses, numbers, pronunciation, emphasis, and pitch using Google Cloud voices.
Quick guide
1. This workspace is SSML-only; the system adds the outer <speak> tag automatically on submit.
SSML editor
Write the inner SSML only. The form adds the root <speak> tag automatically when generating.
1299/2000
Thanh cong cu SSML
Insert snippets quickly or wrap the currently selected text. The root <speak> tag is added automatically.
Within limitYou do not need to type the root <speak> tag.
Limit exceeded by 1,299 chars! Resets at .
Preset templates
Insert common structures with one click.
⌄
Preset templates
Insert common structures with one click.
Supported tags
A short cheat sheet so first-time users understand the tags immediately.
⌄
Supported tags
A short cheat sheet so first-time users understand the tags immediately.
break
<break>Insert a pause in the spoken output.
<break time="500ms"/>say-as
<say-as>Read numbers, dates, and characters with the right interpretation.
<say-as interpret-as="date" format="dmy">10/03/2026</say-as>sub
<sub>Replace spoken output with a friendlier alias.
<sub alias="Google Cloud">GCP</sub>phoneme
<phoneme>Override pronunciation using IPA or another phoneme alphabet.
<phoneme alphabet="ipa" ph="təˈmeɪtoʊ">tomato</phoneme>prosody
<prosody>Adjust speaking rate, pitch, or volume for a section.
<prosody rate="slow" pitch="+2st">Hello everyone</prosody>emphasis
<emphasis>Emphasize a keyword or phrase.
<emphasis level="strong">very important</emphasis>p
<p>Group content into a paragraph.
<p>Paragraph content</p>s
<s>Group content into a sentence.
<s>Sentence content</s>lang
<lang>Temporarily switch the language for a section.
<lang xml:lang="en-US">hello world</lang>mark
<mark>Insert a marker for later synchronization or analytics.
<mark name="section-1"/>audio
<audio>Embed external audio or a short jingle if the engine supports it.
<audio src="https://example.com/sample.mp3">fallback text</audio>voice
<voice>Switch voice within a segment if the backend supports it.
<voice name="en-US-Wavenet-D">Hello world</voice>Voice settings
Show only Google Cloud voices and keep the server-side controls aligned with the home page flow.
Select language
Output
Audio player, request info, and file download.
No audio yet. The player and download button will appear here after a successful generation.
Tutorial Video
Popular AI Tools
Core tools to generate voice, build subtitles, and convert content across common workflows.
Text to Speech
Convert plain text into natural AI voice.
Google TTS Forge
A dedicated SSML workspace for Google Cloud Text to Speech.
SRT to Speech
Generate voiceover synced with subtitle timestamps.
Video to SRT
Extract subtitle blocks from video/audio.
PDF to Speech
Turn PDF content into listenable speech.
OCR
Extract editable text from images and scans.
Speech to Text
Transcribe speech and generate AI summaries.
Related Workflows You Can Run Next
Working with documents? Use PDF to Speech or Document to Speech to convert files directly into audio.
For subtitle-based video workflow, go from Video to SRT to SRT to Speech for timeline-synced dubbing.
For multi-character scripts, use Multi-Voice TTS to assign different voices in one script.
Review, play and download your generated audios. Files will be deleted after 90 days. Download now!
Total: 0 items
| Order | Time | Voice | Text | Pitch | Status | Actions |
|---|---|---|---|---|---|---|
| No items | ||||||
No items
Quick workflow
Designed for both first-time users and SSML-heavy workflows.
- 1
Step 1: Compose SSML
Write directly, start from a preset, or use the quick tag toolbar.
- 2
Step 2: Choose a Google voice
Pick the language and the exact Google voice you need.
- 3
Step 3: Adjust pitch
Use pitch only when you need tonal changes; playback speed stays client-side.
- 4
Step 4: Validate and generate
The form adds the <speak> root automatically before generating audio.
Tip: start from a preset and change one SSML tag at a time so it is easier to compare output.
Why use the Google TTS page?
A cleaner workflow for users who need more control than the home page form.
SSML-first editing
Write inner SSML directly, insert tags from the toolbar, and let the page wrap the final payload with the root <speak> tag.
Faster testing loop
Use quick examples, preset templates, validation, and the supported-tag reference to iterate on pauses, emphasis, and pronunciation faster.
Output and sharing built in
The page keeps quota visibility, downloadable audio, and share-link generation aligned with the main TTS workflow.
Frequently Asked Questions
Q: How is this Google page different from the main Text-to-Speech page?
A: The main page is a broader TTS workspace with many providers and a simpler text-first flow. This Google page is narrower by design: it focuses on Google Cloud voices, inner-SSML editing, tag insertion, validation, and faster iteration for advanced users.
Q: Do I need to type the <speak> root tag myself?
A: No. You only need to write the inner SSML content. The page adds the outer <speak> tag automatically when the generation request is sent.
Q: Can I use plain text instead of SSML here?
A: This workspace is intended for SSML-first usage. If you only need a quick plain-text generation flow, the main TTS page is the better fit.
Q: Are all Google SSML tags supported equally by every voice?
A: Not always. Google Cloud supports a broad SSML subset, but some tags or behaviors can vary by voice family and language. The page includes validation and a supported-tag reference to help you test more safely.
Q: How are credits or character limits handled on this page?
A: The Google page uses the same remaining-credit logic as the home TTS flow. Your visible usage depends on the current voice and the amount of SSML content you submit.
Q: Can I download and share the generated result?
A: Yes. After a successful generation, you can download the audio and copy a share link from the output panel just like in the main TTS experience.