Gemini 3.8 Flash TTS
Audio Available Full comparison ↗ google-deepmind/gemini-3.8-flash-tts · by Google DeepMind
· audio-native-transformer
Pricing — 1 offering(s)
Text input tokens
- $0.50 / 1M tokens (input) Current 2026-09-23 → 2026-12-31
- $1.00 / 1M tokens (input) Future 2027-01-01
Audio output tokens
- $9.00 / 1M tokens (output)
Current
2026-09-23 → 2026-12-31
Standard (paid tier) audio output rate; Google states it as equivalent to $0.00225 per 10s of audio (25 audio…
Standard (paid tier) audio output rate; Google states it as equivalent to $0.00225 per 10s of audio (25 audio tokens per second). Introductory rate through 2026-12-31; the scheduled $18.00/1M ($0.0045 per 10s) from 2027-01-01 is the next row.
- $18.00 / 1M tokens (output) Future 2027-01-01
Cached text input tokens
No current price · last price $0.125 / 1M tokens (cached input), until 2026-10-08
- $0.125 / 1M tokens (cached input) Historical 2026-09-23 → 2026-10-08
Batch
Batch text input tokens
- $0.25 / 1M tokens (input) Current 2026-09-23 → 2026-12-31
- $0.50 / 1M tokens (input) Future 2027-01-01
Batch audio output tokens
- $4.50 / 1M tokens (output) Current 2026-09-23 → 2026-12-31
- $9.00 / 1M tokens (output) Future 2027-01-01
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
See how Gemini 3.8 Flash TTS fits into a cost-aware routing setup
See how →Capability profile
How Gemini 3.8 Flash TTS rates across core capability dimensions, with the task-level evidence behind each rating.
Google positions it as its flagship creative TTS tier (studio-grade fidelity, expressive acting, long-form multi-turn stability). No independent naturalness score found as of 2026-09-27; not rated on vendor positioning alone.
30 prebuilt studio voices, plus an Extended Voice Library of hundreds more (GET /v1beta/voices) and Voice design personas generated from a text description (Google's speech-generation guide).
Voice replication from reference plus consent audio, stored persistently (up to 200 custom voices per project, 1-year retention) or as stateless client-held keys (Google's speech-generation guide).
130 languages per Google's model page, with automatic input-language detection.
Streaming supported (headerless 16-bit PCM at 24 kHz); Google publishes no time-to-first-audio figure.
Ratings are estimated — limited independent data is available for this model.
Operator guidance
Choose over Gemini 3.8 Flash-Lite TTS when fidelity, acting nuance or dialect coverage matter more than cost: same API schema and voices, 130 vs 101 languages, $9 vs $6 per 1M audio output tokens (introductory rates). For high-volume single-speaker read-aloud or voice-agent cascades, Google itself recommends Flash-Lite.
Use cases
- Audiobooks and studio narration (Google's stated best use)
- Complex multi-speaker dialogue and heavy vocal-burst acting
- Regional dialects and difficult pronunciation across 130 languages
Limitations
- No independent quality or latency benchmark found as of 2026-09-27 — capability ratings above rest on Google's own documentation
- Pricing is introductory through 2026-12-31 and doubles on 2027-01-01 (Google's pricing page)
- Token-billed: comparing against per-character TTS needs a tokens-per-character ratio Google does not publish (25 audio tokens per second of output is published)
- Inline text directions from earlier Gemini TTS prompts may now be spoken aloud — prompts need migrating to speech_metadata