This API extends audio tracks while preserving the original style of the audio track. It includes Suno's upload functionality, allowing users to upload audio files for processing. The expected result is a longer track that seamlessly continues the input style.
About this model
Suno-Extend-Music is an advanced API solution designed specifically for extending audio tracks while maintaining the original style and integrity of the music. Leveraging cutting-edge AI models, this tool seamlessly continues your audio tracks by analyzing the provided sample and generating additional segments that are stylistically coherent. With integration of Suno's upload functionality, users simply provide a URL to their audio file and receive a perfectly matched extension in return.
This model capitalizes on state-of-the-art deep learning architectures that prioritize style consistency and audio quality. It offers a flexible configuration through various parameters—such as style specification, vocal gender preferences, and even instrumentals—to deliver results that are both precise and creatively inspired. The ability to control timing and extend tracks exactly where needed gives musicians, content creators, and developers a unique advantage in producing polished, professional, and longer audio tracks effortlessly.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.09 per generation | muapiapp is 20-50% more affordable than its competitors while providing superior quality and consistency in audio track extensions. |
| Fal.ai | $0.12 per generation | Fal.ai's pricing is slightly higher, making muapiapp about 25% cheaper without compromising on performance or output quality. |
| Replicate | $0.12 per generation | Similar to Fal.ai, Replicate offers competitive pricing, but muapiapp stands out as 20-50% more cost-effective with equally impressive results. |
muapiapp is 20-50% more affordable than its competitors while providing superior quality and consistency in audio track extensions.
Fal.ai's pricing is slightly higher, making muapiapp about 25% cheaper without compromising on performance or output quality.
Similar to Fal.ai, Replicate offers competitive pricing, but muapiapp stands out as 20-50% more cost-effective with equally impressive results.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | A description of the desired audio content. The prompt will be strictly used as the lyrics and sung in the generated track. Maximum 3000 characters | Extend the music with more relaxing notes |
| Audio URL | string | The URL for uploading audio files. Ensure the uploaded audio does not exceed 2 minutes in length. | https://d3adwkbyhxyrtq.cloudfront.net/audios/186/755853337445/example.mp3 |
| Style | string | Music style specification for the generated audio. | Classical |
| Custom Mode | boolean | Enable custom mode for advanced settings. | true |
| Title | string | Title for the generated music track (optional). | - |
| Instrumental | boolean | Enable this option to generate music without prompt. If false prompt will used as the exact lyrics. | true |
| Model | Enum (7 options) | The AI model version to use for generation. | V5 |
| Continue At | int | The time point (in seconds) from which to start extending the music. Value range: greater than 0 and less than the total duration of the uploaded audio. Specifies the position in the original track where the extension should begin. | 1 |
| Persona ID | string | Persona ID or custom voice ID to apply to the generated music (optional). Pair with persona_model to disambiguate. | - |
| Persona Model | Enum (2 options) | What kind of persona_id this is. Set to voice_persona when persona_id is a cloned voice ID from suno-voice-clone. Requires model V5 or V5_5. | - |
| Negative Tags | string | Music styles or traits to exclude from the generated audio (optional). Use to avoid specific styles. | null |
| Vocal Gender | Enum (2 options) | Vocal gender preference for the singing voice (optional). | male |
| Style Weight | int | Strength of adherence to the specified style (optional). Range 0–1, up to 2 decimal places. | 0.65 |
| Weirdness Constraint | int | Controls experimental/creative deviation (optional). Range 0–1, up to 2 decimal places. | 0.65 |
| Audio Weight | int | Balance weight for audio features vs. other factors (optional). Range 0–1, up to 2 decimal places. | 0.65 |
A description of the desired audio content. The prompt will be strictly used as the lyrics and sung in the generated track. Maximum 3000 characters
Extend the music with more relaxing notesThe URL for uploading audio files. Ensure the uploaded audio does not exceed 2 minutes in length.
https://d3adwkbyhxyrtq.cloudfront.net/audios/186/755853337445/example.mp3Music style specification for the generated audio.
ClassicalEnable custom mode for advanced settings.
trueTitle for the generated music track (optional).
-Enable this option to generate music without prompt. If false prompt will used as the exact lyrics.
trueThe AI model version to use for generation.
V5The time point (in seconds) from which to start extending the music. Value range: greater than 0 and less than the total duration of the uploaded audio. Specifies the position in the original track where the extension should begin.
1Persona ID or custom voice ID to apply to the generated music (optional). Pair with persona_model to disambiguate.
-What kind of persona_id this is. Set to voice_persona when persona_id is a cloned voice ID from suno-voice-clone. Requires model V5 or V5_5.
-Music styles or traits to exclude from the generated audio (optional). Use to avoid specific styles.
nullVocal gender preference for the singing voice (optional).
maleStrength of adherence to the specified style (optional). Range 0–1, up to 2 decimal places.
0.65Controls experimental/creative deviation (optional). Range 0–1, up to 2 decimal places.
0.65Balance weight for audio features vs. other factors (optional). Range 0–1, up to 2 decimal places.
0.65Developer documentation
Prepare Your Audio
Define Your Input Parameters
Submit Your Request
suno-extend-music endpoint with the prepared JSON payload.Interpreting Results
audio with a URL to your extended audio track.Iterate if Needed
Frequently asked
The API accepts standard audio file formats such as MP3. Ensure that the file is accessible via a URL and does not exceed 2 minutes in duration.
The underlying AI models analyze the characteristics of your uploaded audio and replicate its style using advanced algorithms that balance the prompt inputs and existing audio features. Parameters such as style_weight and audio_weight help guide this process.
Yes, you can specify the 'continue_at' parameter in seconds. This parameter determines the point in the original track where the extension should begin.
Absolutely. By setting the 'instrumental' parameter to true, the API will generate music without vocals, using the provided prompt as guidance for the overall mood and style.