Stable Audio 3 Small Music Base audio to audio fal AI

Prompt

Text description guiding how the source audio should be transformedRequired · prompt

Audio URL

Source audio to transformRequired · audio_url

Duration

Duration of the generated audio in secondsOptional · duration

Seed

Random seed for reproducible outputsOptional · seed

Guidance scale

Classifier-free guidance scaleOptional · guidance_scale

Num inference steps

Number of sampling stepsOptional · num_inference_steps

Bitrate

Audio bitrate for compressed output formats (e.g., mp3, aac, opus)Optional · bitrate

Output format

Container format for the generated audio outputOptional · output_format

Init noise level

How much noise to add to the source audioOptional · init_noise_level

Negative prompt

Text description of qualities to avoid in the outputOptional · negative_prompt

Enable prompt expansion

If True, the prompt will be expanded using an LLM for more detailed and higher quality results (false)Optional · enable_prompt_expansion

Enable safety checker

Enable NSFW content safety checkingOptional · enable_safety_checker

Price

$0.032 per call

Billing

The provider’s price, with no markup. Billed for measured usage.

Price checked

3 November 2026

Your agent reads the schema and the price with inspect_tool before it runs the tool.

MCP call

Copy

cURL command

Copy

TypeScript

Copy

Tool ID

Copy

• Bytedance Seed Speech text to speech fal AI v2fal.ai$0.03/1,000 characters
• Chatterbox text to speech fal AI multilingualfal.ai$0.025/1,000 characters
• Dia text to speech fal AIfal.ai$0.04/1,000 characters
• ElevenLabs forced alignmentfal.ai$0.22/unit
• Gemini 3.8 Flash Lite TTS speech and two-speaker dialoguefal.ai$0.03/1,000 characters
• Gemini 3.8 Flash TTS speech and two-speaker dialoguefal.ai$0.045/1,000 characters
• Grok voicefal.aiUsage based
• Lyria 3 Pro text to audio fal AIfal.ai$0.08
• Compare all 56