Google Cloud Text-to-Speech

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; Teams needing broad API coverage out of the box

Pricing model

Usage-based [2]cloud.google.com/text-to-speech/pricing“Text-to-Speech is priced based on the number of characters sent to the service to be synthesized into audio each month.”

Published pricing

✓ Yes

Free tier

✓ Yes [3]cloud.google.com/text-to-speech/pricing“The first 1 million characters for WaveNet voices are free each month, and for Standard (non-WaveNet) voices, the first 4 million characters are free each month.”

Free tier details

Recurring monthly free allowance: 4 million characters/month for Standard voices; 1 million characters/month for WaveNet voices; 1 million characters/month for Neural2, Studio, and Chirp 3 HD voices. Separate one-time $300 trial credit (90 days) is also available but is not part of the recurring free tier. [4]cloud.google.com/text-to-speech/pricing“The first 1 million characters for WaveNet voices are free each month, and for Standard (non-WaveNet) voices, the first 4 million characters are free each month.”costbench.com/software/ai-voice-tools/google-cloud-text-to-speech/free-plan/“Standard Voices: 4M characters/month; Neural2 Voices: 1M characters/month; Studio Voices: 1M characters/month; Chirp 3 HD Voices: 1M characters/month”

Self-serve signup

✓ Yes [5]docs.cloud.google.com/billing/docs/how-to/create-billing-account“To create a self-serve Cloud Billing account, you sign in to the Manage billing accounts page in the Google Cloud console and click Create account.”

Requires sales call

✗ No

Enterprise plan

✓ Yes

• Real-time streaming
• Voice cloning
• SSML control
• Multilingual voices
• Word timestamps

Supported actions

synthesize_speech, streaming_tts, long_audio_synthesis, ssml_support, instant_voice_cloning, multilingual_synthesis, multi_speaker_markup, word_timestamps, custom_pronunciations, speaking_rate_control, pitch_control, volume_control, list_voices, async_long_audio_synthesis, multi_speaker_audio [6]docs.cloud.google.com/text-to-speech/docs/reference/rest“POST /v1/text:synthesize - Synchronous speech synthesis; POST /v1/{parent=projects/*/locations/*}:synthesizeLongAudio - Asynchronous long-form synthesis”docs.cloud.google.com/text-to-speech/docs/chirp3-instant-custom-voice“Reference and consent audio files generate a 'voice cloning key'—a text string representing the voice data stored client-side.”docs.cloud.google.com/text-to-speech/docs/chirp3-hd“Chirp 3: HD supports streaming synthesis through the streaming_synthesize() API method, enabling real-time audio generation as text is streamed in chunks.”

Regions

global, us (multi-region), eu (multi-region), us-central1, asia-northeast1 (Tokyo), australia-southeast1 (Sydney), asia-south1 (Mumbai), asia-southeast1 (Singapore), asia-northeast3 (Seoul), europe-west2 (London), europe-west3 (Frankfurt), europe-west4 (Netherlands), northamerica-northeast1 [7]docs.cloud.google.com/text-to-speech/docs/endpoints“US: https://us-texttospeech.googleapis.com; EU: https://eu-texttospeech.googleapis.com; US Central1: https://us-central1-texttospeech.googleapis.com; Asia Pacific: Tokyo, Sydney, Mumbai, Singapore, Seoul; European: London, Frankfurt, Eemshaven”

Languages

Afrikaans (af-ZA), Arabic (ar-XA), Basque (eu-ES), Bengali (bn-IN), Bulgarian (bg-BG), Catalan (ca-ES), Chinese - Hong Kong (yue-HK), Croatian (hr-HR), Czech (cs-CZ), Danish (da-DK), Dutch - Belgium (nl-BE), Dutch - Netherlands (nl-NL), English - Australia (en-AU), English - India (en-IN), English - UK (en-GB), English - US (en-US), Estonian (et-EE), Filipino (fil-PH), Finnish (fi-FI), French - Canada (fr-CA), French - France (fr-FR), Galician (gl-ES), German (de-DE), Greek (el-GR), Hebrew (he-IL), Hindi (hi-IN), Hungarian (hu-HU), Indonesian (id-ID), Italian (it-IT), Japanese (ja-JP), Korean (ko-KR), Latvian (lv-LV), Lithuanian (lt-LT), Mandarin Chinese (cmn-CN), Mandarin Chinese - Taiwan (cmn-TW), Norwegian (nb-NO), Polish (pl-PL), Portuguese - Brazil (pt-BR), Portuguese - Portugal (pt-PT), Punjabi - India (pa-IN, Preview), Romanian (ro-RO), Russian (ru-RU), Serbian (sr-RS), Slovak (sk-SK), Slovenian (sl-SI), Spanish - Spain (es-ES), Spanish - US (es-US), Swedish (sv-SE), Thai (th-TH), Turkish (tr-TR), Ukrainian (uk-UA), Vietnamese (vi-VN), 80+ languages and variants via Gemini-TTS models [8]docs.cloud.google.com/text-to-speech/docs/gemini-tts“Gemini-2.5 TTS Flash and Pro in GA with capabilities for 30 speakers across 80+ locales”docs.cloud.google.com/text-to-speech/docs/list-voices-and-types“Cloud TTS generates audio with natural, human-like quality, which creates speech that sounds like a real person.”

Input types

plain text, SSML [9]docs.cloud.google.com/text-to-speech/docs/basics“Raw text; Speech Synthesis Markup Language (SSML) - a supported subset of available elements”

Output types

MP3, LINEAR16 (WAV), OGG_OPUS, MULAW, ALAW, PCM, streaming audio chunks [10]docs.cloud.google.com/text-to-speech/docs/basics“MP3; LINEAR16 (the encoding used in WAV files)”docs.cloud.google.com/text-to-speech/docs/chirp3-hd“Streaming: ALAW, MULAW, OGG_OPUS, PCM; Batch: ALAW, MULAW, MP3, OGG_OPUS, PCM”

Webhooks

✗ No

Sandbox / test mode

✗ No [11]cloud.google.com/text-to-speech/pricing“You must enable billing to use Text-to-Speech, and will be automatically charged if your usage exceeds the number of free characters allowed per month.”

SDK languages

Python, Node.js, Java, Go, C#, PHP, Ruby, C++ [12]docs.cloud.google.com/text-to-speech/docs/libraries“Client libraries make it easier to access Google Cloud APIs from a supported language. C++, C#, Go, Java, Node.js, PHP, Python, Ruby”

MCP server

✗ No [13]docs.cloud.google.com/mcp/supported-products“Text-to-Speech does not appear in any of the three comprehensive tables provided (Google Cloud MCP servers, Google MCP servers, Google Workspace MCP servers).”

SOC 2

SOC 2 Type II [14]cloud.google.com/security/compliance/soc-2“Google Cloud only issues SOC 2 Type II reports. The core Google Cloud and Google Workspace SOC 2 Type II reports are issued quarterly and can be downloaded via the Compliance Reports Manager.”

HIPAA

✓ Yes [15]cloud.google.com/security/compliance/hipaa“Text-to-Speech is explicitly listed as a covered product under the Google Cloud BAA for HIPAA compliance.”

GDPR

✓ Yes [16]cloud.google.com/security/compliance“Our products regularly undergo independent verification of security, privacy, and compliance controls, achieving certifications against global standards.”

ISO 27001

✓ Yes [17]cloud.google.com/security/compliance/iso-27001“The Google Cloud Services ISMS has received an accredited ISO/IEC 27001 certification after undergoing an audit by an independent third party.”

PCI DSS

– Unknown [18]cloud.google.com/security/compliance/pci-dss

Published SLA

✓ Yes [19]cloud.google.com/text-to-speech/sla“Text-to-Speech Service Level Agreement (SLA) | Google Cloud”

Rate limits

Maximum request size: 5,000 bytes per request (cannot be increased). Requests per minute (RPM) by voice type: Chirp 3 HD: 200 RPM; Chirp Voice Cloning: 30 RPM; Neural2: 1,000 RPM; Polyglot: 1,000 RPM; Studio: 500 RPM; Long Audio Synthesis: 100 RPM; General (all other voices): 1,000 RPM. Concurrent streaming sessions: 100 per project. Voice cloning key generation: 10 requests per minute. Gemini-2.5-flash-tts: 150 QPM; Gemini-2.5-pro-tts: 125 QPM. [20]docs.cloud.google.com/text-to-speech/quotas“Maximum request size: 5,000 bytes total per request. Chirp 3: 200 RPM; Neural 2: 1,000 RPM; Studio: 500 RPM; General (all other voices): 1,000 RPM; Concurrent streaming sessions: 100 per project; Voice cloning key generation: 10 requests per minute”docs.cloud.google.com/text-to-speech/quotas“gemini-2.5-flash-tts: 150 QPM; gemini-2.5-pro-tts: 125 QPM”

Known restrictions

Cloud TTS does not support all SSML elements for all available languages., Instant Voice Cloning (Chirp 3) is currently restricted to allow-listed users; contact sales to request access., Voice cloning requires consent audio recording with the statement: 'I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.', Maximum request size of 5,000 bytes cannot be increased., Chirp 3: HD voices are out of scope for regionalization and data residency despite being available in eu/us endpoints., Reference audio for instant voice cloning must be up to 10 seconds, single-channel, with minimal background noise. [21]docs.cloud.google.com/text-to-speech/docs/chirp3-instant-custom-voice“Currently restricted to allow-listed users. Contact the sales team to request access. Users must record the required consent statement: 'I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model.'”docs.cloud.google.com/text-to-speech/docs/basics“Cloud TTS does not support all SSML elements for all available languages.”

• Docs
• Status page

Docs rendering: static

API style

rest

Base URL

https://texttospeech.googleapis.com

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key, oauth2

Idempotency keys

✗ No

Error format

vendor-specific

Rate limit

1000 / minute

SDKs

• Python google-cloud-texttospeech · repo
• Node.js @google-cloud/text-to-speech · repo
• Java com.google.cloud:google-cloud-texttospeech · repo
• Go cloud.google.com/go/texttospeech/apiv1 · repo
• C# Google.Cloud.TextToSpeech.V1 · repo
• PHP google/cloud-text-to-speech · repo
• Ruby google-cloud-text_to_speech · repo
• C++ · repo

• Auth docs
• Quickstart
• Deprecation policy

Launched

2017-11-10

GA

2018-08-28

Notable customers

Ingram Content Group

• ElevenLabs Text to Speech

  "Text to Speech with high quality, human-like AI voices"

  Hybrid · free tier · public pricing · self-serve

• Azure AI Text to Speech

  "Text to speech enables your applications, tools, or devices to convert text into human like synthesized speech. The text to speech capability is also known as speech synthesis. Use human like standard voices out of the box, or create a custom voice that's unique to your product or brand."

  Usage · free tier · public pricing · self-serve

• Amazon Polly

  "Amazon Polly is a cloud service that converts text into lifelike speech. You can use Amazon Polly to develop applications that increase engagement and accessibility."

  Usage · free tier · public pricing · self-serve

• Cartesia (Sonic)

  "The fastest and most natural text to speech model"

  Hybrid · free tier · public pricing · self-serve

• Murf AI

  "Enterprise-grade AI voice generation with 150+ natural-sounding voices across 35 languages and 20+ speaking styles."

  Usage · public pricing · self-serve

• OpenAI Text to Speech (gpt-4o-mini-tts / tts-1)

  "Transform text into lifelike spoken audio" - OpenAI's TTS service enabling blog narration, multilingual audio production, and realtime voice output via gpt-4o-mini-tts, tts-1, and tts-1-hd models.

  Usage · public pricing · self-serve

Google Cloud Text-to-Speech alternatives · Google Cloud Text-to-Speech vs ElevenLabs Text to Speech · All Text-to-Speech APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: docs.cloud.google.com
2. ↑Pricing model: cloud.google.com
3. ↑Free tier: cloud.google.com
4. ↑Free tier details: cloud.google.com · costbench.com
5. ↑Self-serve signup: docs.cloud.google.com
6. ↑Supported actions: docs.cloud.google.com · docs.cloud.google.com · docs.cloud.google.com
7. ↑Regions: docs.cloud.google.com
8. ↑Languages: docs.cloud.google.com · docs.cloud.google.com
9. ↑Input types: docs.cloud.google.com
10. ↑Output types: docs.cloud.google.com · docs.cloud.google.com
11. ↑Sandbox: cloud.google.com
12. ↑SDK languages: docs.cloud.google.com
13. ↑MCP server: docs.cloud.google.com
14. ↑SOC 2: cloud.google.com
15. ↑HIPAA: cloud.google.com
16. ↑GDPR: cloud.google.com
17. ↑ISO 27001: cloud.google.com
18. ↑PCI DSS: cloud.google.com
19. ↑Published SLA: cloud.google.com
20. ↑Rate limits: docs.cloud.google.com · docs.cloud.google.com
21. ↑Known restrictions: docs.cloud.google.com · docs.cloud.google.com

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"ssml":true,"streaming":true,"multilingual":true,"voice_cloning":true,"word_ti…
2. 2026-06-21 Summary Md: (none) → Google Cloud Text-to-Speech converts text or SSML input into natural-sounding a…
3. 2026-06-21 Score Docs Quality: (none) → 15
4. 2026-06-21 Score Procurement Friction: (none) → 100
5. 2026-06-21 Score Trust Readiness: (none) → 90
6. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
7. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
8. 2026-06-21 Score Agent Friendliness: (none) → 20
9. 2026-06-21 Score Pricing Transparency: (none) → 100
10. 2026-06-21 Score Setup Speed: (none) → 85
11. 2026-06-21 Llms Txt Present: (none) → No
12. 2026-06-21 Has Structured Data: (none) → No
13. 2026-06-21 Robots Allows Agents: (none) → Yes
14. 2026-06-21 Status Page URL: (none) → https://status.cloud.google.com
15. 2026-06-21 Docs URL: (none) → https://docs.cloud.google.com/?hl=zh-tw
16. 2026-06-21 Rendering: (none) → static
17. 2026-06-21 SDK Packages: set to Python, Node.js, Java, Go, C#, PHP, Ruby, C++
18. 2026-06-21 MCP Server Available: set to No
19. 2026-06-21 Pricing Model: set to usage_based
20. 2026-06-21 Has Published Pricing: set to Yes
21. 2026-06-21 Free Tier Available: set to Yes
22. 2026-06-21 Free Tier Details: set to Recurring monthly free allowance: 4 million characters/month for Standard voice…
23. 2026-06-21 Self Serve Signup: set to Yes
24. 2026-06-21 Requires Sales Call: set to No
25. 2026-06-21 Enterprise Plan Available: set to Yes
26. 2026-06-21 SOC 2: set to type_2
27. 2026-06-21 HIPAA: set to Yes
28. 2026-06-21 GDPR: set to Yes
29. 2026-06-21 ISO 27001: set to Yes
30. 2026-06-21 SLA Published: set to Yes
31. 2026-06-21 SLA URL: set to https://cloud.google.com/text-to-speech/sla
32. 2026-06-21 Data Retention Policy URL: set to https://cloud.google.com/terms/cloud-privacy-notice
33. 2026-06-21 Documented Rate Limits: set to Maximum request size: 5,000 bytes per request (cannot be increased). Requests p…
34. 2026-06-21 Rate Limit Requests: set to 1000
35. 2026-06-21 Rate Limit Window: set to minute
36. 2026-06-21 Auth Docs URL: set to https://docs.cloud.google.com/text-to-speech/docs/authentication
37. 2026-06-21 API Style: set to rest
38. 2026-06-21 Base URL: set to https://texttospeech.googleapis.com
39. 2026-06-21 API Version: set to v1
40. 2026-06-21 Versioning Scheme: set to url
41. 2026-06-21 Stability: set to ga
42. 2026-06-21 Deprecation Policy URL: set to https://cloud.google.com/terms/deprecation
43. 2026-06-21 Quickstart URL: set to https://docs.cloud.google.com/text-to-speech/docs/create-audio-text-client-libr…
44. 2026-06-21 Idempotency Supported: set to No
45. 2026-06-21 Error Format: set to vendor-specific
46. 2026-06-21 Slug: set to google-text-to-speech
47. 2026-06-21 Starting Price Usd: set to 4
48. 2026-06-21 Price Basis: set to 1M characters
49. 2026-06-21 Free Tier Limit: set to 4 million characters/month (Standard voices); 1 million characters/month (WaveN…
50. 2026-06-21 Launched At: set to 2017-11-10

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/google-text-to-speech \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/google-text-to-speech/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →