Capabilities
Explore what Gemini 2.5 Flash TTS supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Google Gemini
- Product
- Text-to-Speech
- Release Date
- May 20, 2025
- Data Policy
- Configurable
- Region
- Global
- Input
- Text
- Output
- Audio
Playground
Try Gemini 2.5 Flash TTS by Google Gemini. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Gemini 2.5 Flash TTS.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Google Gemini | Not specified | Audio | $14.28 / 1M characters | — | gemini/gemini-2.5-flash-tts:gemini |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 30000 |
| Formats | wav, pcm |
Provider Notes
All three Gemini TTS previews support one or two speakers and unary Interactions or generateContent requests. Only Gemini 3.1 Flash TTS supports streaming and AudioLab can transcode its native 24 kHz mono PCM to the common output formats. The Gemini 2.5 TTS models reject both streaming transports and expose only PCM or WAV through AudioLab; request response_format=wav for a self-describing audio file. Preview models require exact selection and are excluded from managed tts/* aliases.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini/gemini-2.5-flash-tts",
"input": "Make every word count.",
"voice": "auto",
"response_format": "wav"
}' --output speech.wavRequest Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | gemini/gemini-2.5-flash-tts — Required model identifier. |
transport | View Accepted Values |
speech_config | View Accepted Values |
response_format | View Accepted Values |
store | View Accepted Values |
max_output_tokens | View Accepted Values |
seed | View Accepted Values |
stop_sequences | View Accepted Values |
temperature | View Accepted Values |
top_p | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 30000 |
| Formats | wav, pcm |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Gemini 3.1 Flash TTSGoogle Gemini | Not specified | $28.56 / 1M characters | — |
| Gemini 2.5 Pro TTSGoogle Gemini | Not specified | $28.56 / 1M characters | — |
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| tts-rt-v2Soniox | Not specified | $11.985 / 1M characters | — |
| Inworld TTS-2 FlashInworld AI | Not specified | $12.75 / 1M characters | — |
