GET
/v1/schemas/fal/audio/fal-ai/gemini-3.1-flash-tts
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace557d35fc8d1e4eaae52a7025164b9c81d9beb2ef76e37663a608402a302787f9{
"fetchedAt": 1793941202,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
8 properties · 1 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| prompt* | string | The text to convert to speech. Gemini 3.1 Flash TTS supports natural-language prompting for style, pace, accent, and emotional expression — include delivery instructions inline with the text (e.g. 'Say cheerfully: Have a wonderful day!'). Supports expressive a… | length ≥ 1 · length ≤ 50000 |
| enable_safety_checker | boolean | Check input content for safety. Disabling requires account authorization. | default: true |
| output_format | enum | Audio output format. mp3: compressed, small file size (recommended). wav: uncompressed PCM wrapped in WAV (24 kHz, 16-bit mono). ogg_opus: Ogg container with Opus codec, good quality-to-size ratio. | wav | mp3 | ogg_opus · default: "mp3" |
| voice | enum | Voice preset for single-speaker synthesis. 30 distinct voices are available. Ignored when speakers is set. Popular choices: Kore (strong, firm female), Puck (upbeat, lively male), Charon (calm, professional male), Zephyr (bright, clear female), Aoede (warm, me… | Achernar | Achird | Algenib | Algieba | Alnilam | Aoede · +24 more · default: "Kore" |
| temperature | number | Controls the randomness of the speech output. Higher values produce more creative and varied delivery, while lower values make the output more predictable and focused. | 0 ≤ n ≤ 2 · default: 1 |
| speakers | SpeakerConfig[] | any[] | Multi-speaker voice configuration. When set, enables multi-speaker synthesis where different parts of the text are spoken by different voices. Each speaker needs a voice and a speaker_id (alias) that matches prefixes in the prompt. | nullable |
| style_instructions | string | Optional style and delivery instructions prepended to the prompt. Controls expressiveness, accent, pace, tone, and emotional expression using natural language. Use this to separate style control from the text content. Examples: 'Speak warmly and slowly', 'Read this as a dramatic newscast', 'Use a British accent with a cheerful tone', 'Whisper mysteriously'. | length ≤ 4000 · nullable |
| language_code | enum | Language for multilingual synthesis. When set, steers the model to speak in the specified language. If not set, the model auto-detects the language from the text. | Arabic (Egypt) | Bangla (Bangladesh) | Dutch (Netherlands) | English (India) | English (US) | French (France) · +81 more · nullable |
Types
1 $defsSpeakerConfigobject
Voice configuration for a single speaker in multi-speaker synthesis.
| voice* | enum | Voice preset for this speaker. | Achernar | Achird | Algenib | Algieba | Alnilam | Aoede · +24 more |
| speaker_id* | string | Alias used to identify this speaker in the prompt. Use this alias as a prefix in the prompt field, e.g. 'Alice: Hello! Bob: Hi there!'. Must be alphanumeric with no whitespace. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/gemini-3.1-flash-tts","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}