Google's Gemini TTS converts text to realistic audio. 30 voice presets, multi-speaker synthesis (up to 10 speakers), 24+ languages, and inline style markers for expressive control.
pip install requestsimport requests
response = requests.post(
"https://api.runflow.io/v1/run/gemini-tts",
headers={"Authorization": "Bearer RUNFLOW_API_KEY"},
json={
"prompt": "Your prompt here",
"output_format": "mp3"
},
)
data = response.json()
print(data["audio"]["url"])| Parameter | Type | Description |
|---|---|---|
| prompt | string | The text to convert to speech. Gemini 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!'). For multi-speaker synthesis, prefix lines with speaker aliases defined in the speakers field (e.g. 'Alice: Hello!\nBob: Hi!'). Supports inline pace/style markers like [slowly], [whispering], [excited], [extremely fast]. |
| speakers | string | 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. Requires gemini-2.5-pro-tts or gemini-2.5-flash-tts model. Not supported with gemini-2.5-flash-lite-preview-tts. |
| output_format | string | 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. |
| model | string | Which Gemini TTS model to use. gemini-2.5-flash-tts: low latency, cost-efficient for everyday applications (recommended). gemini-2.5-pro-tts: highest quality, best for structured workflows like podcasts, audiobooks, and customer support. |
| voice | string | 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, melodic female). |
| language_code | string | Language for multilingual synthesis. When set, steers the model to speak in the specified language. Supports 24 GA languages and 60+ Preview languages. If not set, the model auto-detects the language from the text. |
| 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. |
| 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'. |
| Field | Type | Description |
|---|---|---|
| audio | string | The generated audio file. |
Get API access in minutes. No GPU setup, no infrastructure to manage.