Create Character Voices
Transform a single voice recording into distinct character voices for games, animations, and storytelling.
Voice Transformer
Voice swap with emotion preserved
Convert an audio recording into a different voice while preserving pacing, emotion, and delivery. Provide source audio and a target voice ID for speech-to-speech conversion. For anonymization, dubbing, localization, and brand voice matching. Includes noise removal.
Transform Voice
Convert speech audio into a different voice while preserving the original emotion, delivery, and pacing. Provide a source audio URL and a target voice ID to produce a transformed audio file with fine-grained control over stability, similarity, and style.
Returns: Transformed audio file path (auto-uploaded), target voice ID, model ID, noise removal status, output format, and file size
Parameters
audio_url *stringURL of the source audio file to transform. Must be a publicly accessible URL (MP3, WAV, or other common audio format).
voice_id *stringVoice ID of the target voice. Use the voice-generator list_voices action to browse available voices.
model_idstringSpeech-to-speech model to use. Defaults to "eleven_english_sts_v2".
stabilitynumberVoice stability (0-1). Lower values produce more expressive and variable output. Higher values produce more consistent results.
similarity_boostnumberSimilarity boost (0-1). Higher values make the output more closely match the target voice. Lower values allow more creative variation.
stylenumberStyle exaggeration (0-1). Higher values amplify the style of the target voice. Recommended to keep low for natural results.
remove_background_noisebooleanWhether to remove background noise from the source audio before transformation. Defaults to false.
seednumberRandom seed for reproducible transformations. Same seed with same input should produce similar results.
output_formatstringAudio output format and quality. Defaults to "mp3_44100_128". Higher bitrate means better quality but larger files.
Example
Transform a podcast clip into a different voice with default settings
curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
-d '{
"tool": "voice-transformer",
"skill": "transform_voice",
"input": {
"audio_url": "https://example.com/podcast-clip.mp3",
"voice_id": "JBFqnCBsd6RMkjVDRZzb"
}
}' \
https://api.toolrouter.com/v1/tools/callQuick Start
MCP (Claude Code)
claude mcp add --transport stdio \
--env TOOLROUTER_API_KEY=YOUR_API_KEY \
toolrouter -- npx -y toolrouter-mcpREST API
curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
-d '{"tool":"voice-transformer","skill":"transform_voice","input":{}}' \
https://api.toolrouter.com/v1/tools/callUse Cases
Anonymize Voice Recordings
Transform voice recordings to conceal speaker identity while preserving speech content and intelligibility.
Dub Marketing Videos
Translate and dub your marketing videos into multiple languages to reach international audiences.
Remove Background Noise from Recordings
Clean up recordings by removing background noise, hum, wind, and environmental sounds.
Workflows
Voice Branding Kit
Build a complete sonic brand identity with custom AI voice, voice transformations, and signature sound design.
Frequently Asked Questions
What does voice transformation actually change?
It swaps the voice while keeping the pacing, emotion, and delivery of the original recording.
Do I need a target voice ID?
Yes. Pick a voice with `list_voices`, then pass that `voice_id` into `transform_voice`.
Can it clean up background noise too?
Yes. Turn on background-noise removal when the source audio has ambient noise or room tone.
Is it language-agnostic?
The default model is English-only, so that is the safest assumption unless the tool output says otherwise.